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. 8712
    Prev
    Next
    INDEX
    Explanations

    mentions of specific characters or entities with special characters in their names

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols, particularly those often associated with encoding issues

    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
    oids
    -1.07
    oidal
    -0.95
    oid
    -0.87
    apsed
    -0.75
    oresc
    -0.68
     Icar
    -0.68
    oted
    -0.67
     Orion
    -0.67
    dfx
    -0.67
     drawer
    -0.67
    POSITIVE LOGITS
    âĤ¬
    1.25
    ¯¯
    0.96
    ¯
    0.96
    ©
    0.93
    ¯¯¯¯
    0.89
    ¢
    0.89
    tre
    0.89
    ´
    0.89
    ternity
    0.88
    Ô
    0.87
    Activations Density 0.026%

    No Known Activations