© 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. 4-RES-JB
    11. 14762
    Prev
    Next
    INDEX
    Explanations

    mentions of sentences with legal consequences, specifically focusing on prison sentences

    oai_token-act-pair · gpt-3.5-turbo

    mentions of prison sentences and related legal consequences

    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
    xit
    -0.78
    tick
    -0.70
    ween
    -0.70
    amins
    -0.67
    endor
    -0.67
    Birth
    -0.66
    flush
    -0.64
    alter
    -0.63
    LAN
    -0.63
    yip
    -0.63
    POSITIVE LOGITS
     sentences
    0.95
     sentence
    0.89
     jail
    0.82
     jailed
    0.81
     detain
    0.80
     imprisonment
    0.80
     sentenced
    0.79
     rehabilitation
    0.77
    agy
    0.76
     custody
    0.75
    Activations Density 0.035%

    No Known Activations