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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 23765
    Prev
    Next
    INDEX
    Explanations

    the symbol '~' followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the tilde symbol (~)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Luther
    -0.78
    iant
    -0.75
    plom
    -0.71
     Dynamics
    -0.68
     underest
    -0.68
     Bulgar
    -0.67
     Jinn
    -0.67
    matic
    -0.66
    agn
    -0.66
     undes
    -0.66
    POSITIVE LOGITS
    =~=~
    1.20
    #$
    1.03
    ãģ¦
    0.89
     ~
    0.88
    ã
    0.81
    _>
    0.80
    nom
    0.79
    GW
    0.78
    {{
    0.77
    fill
    0.76
    Activations Density 0.012%

    No Known Activations