© 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. 1-RES-JB
    11. 20008
    Prev
    Next
    INDEX
    Explanations

    references to punitive actions or consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to punishment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eds
    -0.89
    ergy
    -0.80
    rote
    -0.75
    oir
    -0.75
    NetMessage
    -0.73
    aug
    -0.72
    ocal
    -0.72
    sonian
    -0.71
    roots
    -0.70
    soDeliveryDate
    -0.69
    POSITIVE LOGITS
     punishment
    1.29
     punishments
    1.16
     punish
    1.05
     punished
    1.04
     inflicted
    0.97
     sanction
    0.93
    ishment
    0.92
     humiliation
    0.89
     lashes
    0.89
     exha
    0.87
    Activations Density 0.015%

    No Known Activations