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

    Neuronpedia

    Jacobian LensNEW
    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. 22254
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and consequences

    oai_token-act-pair · gpt-3.5-turbo

    statements related to causes and consequences

    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
     badass
    -0.92
    !'"
    -0.92
     goddamn
    -0.91
    .'"
    -0.91
    ,'"
    -0.85
     yours
    -0.85
    !'
    -0.84
    ?'"
    -0.83
     ain
    -0.81
     marvelous
    -0.79
    POSITIVE LOGITS
     apologised
    1.07
     licences
    1.06
     emphas
    1.04
     analys
    1.01
     recognised
    1.00
     realised
    0.99
     organisers
    0.98
     counselling
    0.98
     organis
    0.96
     organisations
    0.95
    Activations Density 0.968%

    No Known Activations