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. 9-RES-JB
    6. 11136
    Prev
    Next
    INDEX
    Explanations

    locations or dates

    oai_token-act-pair · gpt-3.5-turbo

    empty tokens or sections within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llor
    -0.69
     fortun
    -0.69
     lik
    -0.65
     nailed
    -0.63
    emale
    -0.61
     withd
    -0.61
    minist
    -0.60
     convol
    -0.60
     vulner
    -0.60
    0000000000000000
    -0.60
    POSITIVE LOGITS
    clusions
    0.92
    clus
    0.91
    activated
    0.86
    CLUS
    0.83
    version
    0.81
     Detail
    0.79
    humans
    0.79
    icio
    0.79
    cluded
    0.77
    STRUCT
    0.77
    Activations Density 0.038%

    No Known Activations