© 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. 7-RES-JB
    11. 13426
    Prev
    Next
    INDEX
    Explanations

    words related to criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to crime and criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arity
    -0.76
     Centauri
    -0.76
    estine
    -0.76
    )=(
    -0.75
    ersed
    -0.70
    hetically
    -0.70
    pread
    -0.69
    artney
    -0.68
    mate
    -0.68
    por
    -0.68
    POSITIVE LOGITS
     spree
    1.06
    fighting
    0.91
    fighter
    0.86
    ously
    0.83
     perpetrated
    0.77
     lord
    0.76
    fighters
    0.75
     unfocusedRange
    0.74
     Victim
    0.74
     crimes
    0.74
    Activations Density 0.039%

    No Known Activations