© 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. 7-RES-JB
    11. 10047
    Prev
    Next
    INDEX
    Explanations

    keywords related to software or technical problems

    oai_token-act-pair · gpt-3.5-turbo

    discussions about various issues or problems encountered

    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
    tsky
    -0.95
    theless
    -0.81
    emouth
    -0.80
    ensions
    -0.80
    ramid
    -0.79
    incoln
    -0.75
    urses
    -0.75
    glas
    -0.74
    achev
    -0.73
    uton
    -0.73
    POSITIVE LOGITS
     plag
    1.20
     affecting
    0.87
    hooting
    0.86
     arise
    0.81
     unresolved
    0.77
     relating
    0.77
     tracker
    0.76
     stemming
    0.76
     resolved
    0.76
     arising
    0.75
    Activations Density 0.042%

    No Known Activations