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. 0-RES-JB
    6. 8457
    Prev
    Next
    INDEX
    Explanations

    adjectives describing strength, stability, or reliability

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "solid."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.74
    bugs
    -0.71
    raid
    -0.70
    may
    -0.68
    gate
    -0.67
    dress
    -0.66
     Gamble
    -0.66
    handler
    -0.66
    orters
    -0.66
    say
    -0.65
    POSITIVE LOGITS
     solid
    3.46
    solid
    2.55
    Solid
    2.14
     Solid
    1.89
     solidly
    1.55
     stellar
    1.32
     sturdy
    1.32
     steady
    1.28
     decent
    1.23
     cement
    1.23
    Activations Density 0.021%

    No Known Activations