© 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. 9-RES-JB
    11. 2481
    Prev
    Next
    INDEX
    Explanations

    violent or aggressive actions between individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isSpecialOrderable
    -0.83
     Pione
    -0.79
     Legislation
    -0.75
     Recomm
    -0.74
     Sturgeon
    -0.73
     Funding
    -0.73
     Revenue
    -0.71
     weddings
    -0.71
     marriages
    -0.70
     Awards
    -0.69
    POSITIVE LOGITS
     unconscious
    1.24
     limp
    1.12
     slumped
    1.09
     sob
    1.07
     bleeding
    1.03
     screaming
    1.03
     kneeling
    1.01
     crying
    1.01
     handcuffed
    1.00
     calmed
    1.00
    Activations Density 0.395%

    No Known Activations