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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7-RES-JB
    6. 20994
    Prev
    Next
    INDEX
    Explanations

    references to the programming language Perl, specifically focusing on versions and features

    oai_token-act-pair · gpt-3.5-turbo

    references to the programming language Perl and its related components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndra
    -0.80
    hs
    -0.75
    HR
    -0.75
    llan
    -0.71
    XT
    -0.69
    éĹĺ
    -0.68
    robe
    -0.68
    IGH
    -0.68
     Doodle
    -0.66
     Otto
    -0.66
    POSITIVE LOGITS
    uvian
    0.91
    anguage
    0.89
    mers
    0.80
    quer
    0.76
    ions
    0.75
     cord
    0.74
    azine
    0.74
    ococ
    0.74
    monary
    0.72
     cords
    0.70
    Activations Density 0.043%

    No Known Activations