Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10339
    Prev
    Next
    INDEX
    Explanations

    mentions of places or geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to public figures and their actions or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]."
    -1.10
    ?).
    -1.06
    .).
    -1.05
    )."
    -1.02
    !).
    -1.00
    }.
    -0.96
    ).
    -0.95
    )).
    -0.95
    %).
    -0.90
    ).[
    -0.88
    POSITIVE LOGITS
    ecause
    0.49
     Churchill
    0.48
     Cardiff
    0.47
    ':
    0.47
     Albion
    0.46
    resa
    0.45
    ousy
    0.44
     Gamble
    0.44
     Proposition
    0.44
    owered
    0.44
    Activations Density 4.037%

    No Known Activations