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. 8-RES-JB
    6. 21897
    Prev
    Next
    INDEX
    Explanations

    comparisons using the word "like"

    oai_token-act-pair · gpt-3.5-turbo

    metaphors and comparisons in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ason
    -0.71
     Ezek
    -0.70
    everal
    -0.69
    ename
    -0.66
    elfth
    -0.66
    rade
    -0.65
    rue
    -0.65
    mber
    -0.65
    aven
    -0.63
    oubted
    -0.63
    POSITIVE LOGITS
     except
    0.99
     minus
    0.84
     Except
    0.84
     wherein
    0.79
    minus
    0.74
     albeit
    0.74
     whereby
    0.71
     insofar
    0.69
     kinda
    0.66
    ombies
    0.65
    Activations Density 0.464%

    No Known Activations