© 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. 10-RES-JB
    11. 20322
    Prev
    Next
    INDEX
    Explanations

    actions and events in a narrative format

    oai_token-act-pair · gpt-3.5-turbo

    verbs and actions indicating conflict or confrontation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.83
    ancial
    -0.79
    hesda
    -0.71
    obyl
    -0.70
    Brexit
    -0.66
    folk
    -0.66
    £ı
    -0.66
    utterstock
    -0.64
    Gaza
    -0.64
    road
    -0.64
    POSITIVE LOGITS
     himself
    1.43
     him
    1.29
     his
    1.21
     teammate
    0.95
    him
    0.89
     Ack
    0.88
     Daniels
    0.87
     fellow
    0.86
     Peters
    0.84
     Klein
    0.84
    Activations Density 0.445%

    No Known Activations