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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13360
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "unlimited."

    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
    +0.23
    1.2%
    647
    +0.10
    0.5%
    448
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.23
    0.07
    653
    +0.10
    0.07
    554
    +0.09
    -0.12
    Negative Logits
    iquette
    -0.65
    olith
    -0.64
    acle
    -0.62
    acus
    -0.61
    bourg
    -0.61
    geist
    -0.60
    agram
    -0.60
     Drawn
    -0.60
    older
    -0.59
    emis
    -0.58
    POSITIVE LOGITS
     access
    0.85
     amounts
    0.80
     quantities
    0.68
     amount
    0.68
     unrestricted
    0.66
     unlimited
    0.64
     free
    0.62
     mileage
    0.62
     supply
    0.60
     remission
    0.60
    Activations Density 9.565%

    No Known Activations