© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 33319
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of people and places, with some focus on anime-related content

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.38
    1.9%
    481
    +0.17
    0.8%
    67
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    367
    +0.38
    0.23
    232
    +0.17
    0.16
    67
    +0.10
    0.20
    Negative Logits
    mble
    -0.80
    anwhile
    -0.66
    umbnails
    -0.64
    etheless
    -0.63
    ĸļ
    -0.61
    ģĸ
    -0.61
     ($)
    -0.59
    ItemImage
    -0.59
    espie
    -0.58
    uyomi
    -0.58
    POSITIVE LOGITS
     Street
    0.75
    Ps
    0.72
     Avenue
    0.71
    OTA
    0.66
    ont
    0.65
    Ts
    0.64
     Island
    0.64
    Star
    0.64
    Pay
    0.64
    inia
    0.63
    Activations Density 18.284%

    No Known Activations