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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4018
    Prev
    Next
    INDEX
    Explanations

    names and titles related to influential political figures and individuals

    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
    48
    +0.16
    0.9%
    526
    +0.10
    0.5%
    106
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.24
    288
    +0.10
    0.23
    48
    +0.07
    0.12
    Negative Logits
    ngth
    -0.72
    alling
    -0.63
    acea
    -0.60
    ologue
    -0.59
    omal
    -0.59
    llo
    -0.58
    alse
    -0.54
     OnePlus
    -0.54
    igun
    -0.54
     Gravity
    -0.53
    POSITIVE LOGITS
    soDeliveryDate
    0.70
    nuts
    0.68
    hens
    0.66
    enei
    0.64
    ilion
    0.63
    nut
    0.61
    ifa
    0.61
    wcsstore
    0.61
     Lumpur
    0.60
    ENSE
    0.60
    Activations Density 9.343%

    No Known Activations