© 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. 8-RES-JB
    11. 9907
    Prev
    Next
    INDEX
    Explanations

    instances of actions related to legal processes or investigations

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with legal and physical actions or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adelphia
    -0.68
    yip
    -0.64
    chev
    -0.60
    liction
    -0.60
    icipated
    -0.60
     ][
    -0.58
    xus
    -0.55
    Disk
    -0.55
    zn
    -0.54
     Flavoring
    -0.54
    POSITIVE LOGITS
     accordingly
    1.20
     by
    1.04
     alike
    0.99
     anew
    0.97
     thereafter
    0.90
     BY
    0.84
     respectively
    0.83
     separately
    0.81
    ãĥ¯
    0.80
     therein
    0.77
    Activations Density 0.184%

    No Known Activations