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

    Neuronpedia

    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. 35078
    Prev
    Next
    INDEX
    Explanations

    mentions or occurrences of the name "Mitchell" or variations of it

    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
    +0.14
    0.8%
    582
    +0.12
    0.6%
    274
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.18
    582
    +0.12
    0.04
    659
    +0.09
    0.07
    Negative Logits
    untu
    -0.64
    icative
    -0.63
    ragon
    -0.62
    ciating
    -0.62
    isman
    -0.61
    zac
    -0.61
    alg
    -0.59
    sterdam
    -0.58
     Ducks
    -0.58
    agonist
    -0.57
    POSITIVE LOGITS
    imaru
    0.81
    fork
    0.74
    itch
    0.70
    itching
    0.67
    icago
    0.65
    IELD
    0.62
    hew
    0.60
    urch
    0.59
    aired
    0.58
    ITCH
    0.57
    Activations Density 6.711%

    No Known Activations