© 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. 18725
    Prev
    Next
    INDEX
    Explanations

    words related to official actions or legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    words related to legal or regulatory actions

    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
     cannabin
    -0.84
     wonderfully
    -0.76
     imagination
    -0.76
     unconsciously
    -0.75
     instinctively
    -0.75
     sublime
    -0.74
     passionately
    -0.73
    ometimes
    -0.73
     Tycoon
    -0.71
     Subtle
    -0.71
    POSITIVE LOGITS
    ission
    1.07
    igation
    1.04
    onement
    1.02
    abling
    1.02
    closure
    1.01
    eding
    1.00
    ction
    0.99
    imposed
    0.98
    iminary
    0.98
    estation
    0.98
    Activations Density 0.336%

    No Known Activations