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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 45582
    Prev
    Next
    INDEX
    Explanations

    text related to affiliate links and online promotions

    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
    +0.10
    0.5%
    688
    +0.10
    0.5%
    301
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.10
    0.21
    623
    +0.10
    0.06
    688
    +0.09
    0.08
    Negative Logits
    llan
    -0.71
    STD
    -0.67
     Temper
    -0.66
    ford
    -0.64
    miah
    -0.64
    icus
    -0.64
     Tall
    -0.62
    itate
    -0.61
    imble
    -0.60
     Presbyter
    -0.60
    POSITIVE LOGITS
     giveaways
    1.12
     coupon
    1.12
     coupons
    1.09
     discounts
    1.02
     giveaway
    0.97
     promotions
    0.92
     pricing
    0.92
     auctions
    0.86
     promo
    0.85
     expiration
    0.85
    Activations Density 11.901%

    No Known Activations