© 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. 11-RES-JB
    11. 22507
    Prev
    Next
    INDEX
    Explanations

    descriptions of medical conditions, injuries, and incidents

    oai_token-act-pair · gpt-3.5-turbo

    sentences conveying the outcome of incidents or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     challeng
    -1.02
     millenn
    -0.94
     boycot
    -0.89
     enriched
    -0.82
     embodied
    -0.82
     monopol
    -0.82
     lett
    -0.80
     ingrained
    -0.80
     inertia
    -0.80
     niche
    -0.79
    POSITIVE LOGITS
     Investigators
    1.46
     Authorities
    1.39
     Officers
    1.37
    Investigators
    1.36
    Officers
    1.36
     Detect
    1.35
     Witnesses
    1.31
    Police
    1.30
     Police
    1.29
     Charges
    1.22
    Activations Density 0.184%

    No Known Activations