© 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. 7665
    Prev
    Next
    INDEX
    Explanations

    mentions of criminal incidents or accidents

    oai_token-act-pair · gpt-3.5-turbo

    references to criminal incidents and violence

    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
    izons
    -0.80
     bundles
    -0.75
     portfolios
    -0.75
    ocobo
    -0.74
    docs
    -0.74
    vana
    -0.73
     reserves
    -0.72
    ngth
    -0.71
    Tokens
    -0.70
    ophy
    -0.69
    POSITIVE LOGITS
     perpetrated
    1.03
     occurred
    1.00
     escalate
    0.99
     caused
    0.94
     occurring
    0.93
    Scene
    0.91
     tragic
    0.91
     involving
    0.89
     unsolved
    0.89
     occur
    0.88
    Activations Density 0.504%

    No Known Activations