Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34070
    Prev
    Next
    INDEX
    Explanations

    names of magazines

    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
    +0.16
    0.7%
    508
    +0.13
    0.5%
    288
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.19
    707
    +0.13
    0.08
    561
    +0.12
    0.08
    Negative Logits
    acted
    -0.91
    speaking
    -0.77
    cker
    -0.76
    ident
    -0.74
    Xi
    -0.74
    weak
    -0.73
    ensions
    -0.70
    haul
    -0.70
    ctive
    -0.69
    ghazi
    -0.69
    POSITIVE LOGITS
    azine
    1.11
     subscriptions
    1.06
     publisher
    1.04
     publishers
    0.98
     covers
    0.93
     magazine
    0.92
     magazines
    0.92
    azines
    0.91
     Seym
    0.88
     subscription
    0.86
    Activations Density 6.493%

    No Known Activations