© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 10724
    Prev
    Next
    INDEX
    Explanations

    mentions of craters or containers

    oai_token-act-pair · gpt-3.5-turbo

    references to craters and crates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    govtrack
    -0.79
    ilded
    -0.73
    oga
    -0.73
    ki
    -0.71
    ests
    -0.70
    yo
    -0.69
    ahon
    -0.69
    romy
    -0.69
    ould
    -0.69
    idy
    -0.67
    POSITIVE LOGITS
    lain
    1.02
    士
    0.81
     Sigma
    0.79
     Barnett
    0.72
    ing
    0.69
     crater
    0.69
    cake
    0.65
     berth
    0.64
    ufact
    0.64
    zinski
    0.62
    Activations Density 0.030%

    No Known Activations