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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 17389
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or entities

    oai_token-act-pair · gpt-3.5-turbo

    abbreviated forms or abbreviations of names and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ħ¢
    -0.58
     Pact
    -0.54
    shore
    -0.54
    manship
    -0.53
     unanswered
    -0.52
     Hes
    -0.52
    XM
    -0.51
    gun
    -0.51
     hourly
    -0.50
    code
    -0.50
    POSITIVE LOGITS
    etti
    0.78
    acci
    0.75
    acs
    0.73
    ola
    0.73
    opa
    0.73
    arine
    0.72
    illions
    0.71
    emale
    0.70
    oresc
    0.70
    esta
    0.69
    Activations Density 0.168%

    No Known Activations