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. 6387
    Prev
    Next
    INDEX
    Explanations

    something with multiple characters, usually associated with a technical or specific context

    oai_token-act-pair · gpt-3.5-turbo

    the word "which" as a connector in various contexts

    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
     VIDEOS
    -0.73
    MENTS
    -0.67
    Bas
    -0.66
    STE
    -0.65
    athi
    -0.63
    Behind
    -0.62
    politics
    -0.58
    GY
    -0.57
    BOX
    -0.57
     Penalty
    -0.55
    POSITIVE LOGITS
     incidentally
    1.08
     translates
    1.06
     consists
    1.06
     comprises
    1.03
     specializes
    1.03
     operates
    0.99
     contains
    0.97
     originated
    0.96
     provides
    0.95
     brings
    0.94
    Activations Density 0.125%

    No Known Activations