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. 2-RES-JB
    6. 4743
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or criminal charges

    oai_token-act-pair · gpt-3.5-turbo

    instances of restrictions or bans related to food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.71
    ronic
    -0.70
     accumulation
    -0.68
     Ake
    -0.67
     mimic
    -0.65
    ilty
    -0.65
    aic
    -0.64
    ronics
    -0.64
    rarily
    -0.64
     deform
    -0.63
    POSITIVE LOGITS
    GREEN
    0.77
    packages
    0.75
    Hour
    0.72
     Votes
    0.71
    *)
    0.71
    Hill
    0.69
    Choice
    0.69
     Shots
    0.67
     Caption
    0.66
    Points
    0.66
    Activations Density 0.000%

    No Known Activations