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. 7-RES-JB
    6. 16952
    Prev
    Next
    INDEX
    Explanations

    names of American sports teams and players

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations or sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     showc
    -0.66
    uscript
    -0.63
    pmwiki
    -0.62
    Reviewer
    -0.60
    }}}
    -0.60
     partName
    -0.58
    ophob
    -0.58
    cence
    -0.57
     nostalg
    -0.57
     Editorial
    -0.56
    POSITIVE LOGITS
    escription
    0.70
    ungle
    0.68
     Rivers
    0.60
    agall
    0.58
    ufact
    0.58
     hers
    0.57
     Morales
    0.57
     Murray
    0.56
     Roe
    0.56
    adra
    0.55
    Activations Density 0.366%

    No Known Activations