© 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. 4-RES-JB
    11. 19764
    Prev
    Next
    INDEX
    Explanations

    quotes and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    references to legal proceedings and related actions

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

    No Comments

    Negative Logits
    die
    -0.59
    obyl
    -0.53
    ãĤ¦ãĤ¹
    -0.52
     domest
    -0.51
     fucking
    -0.51
     chicks
    -0.51
     badass
    -0.51
     Goth
    -0.50
     ghetto
    -0.50
    typ
    -0.49
    POSITIVE LOGITS
     briefed
    0.72
     subpoen
    0.68
     prosecutor
    0.66
     prosecutors
    0.66
     Manafort
    0.63
     DOJ
    0.63
     consulting
    0.63
     citing
    0.63
     Reuters
    0.63
     spokeswoman
    0.61
    Activations Density 2.489%

    No Known Activations