© 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. 1736
    Prev
    Next
    INDEX
    Explanations

    phrases related to harrowing or traumatic experiences

    oai_token-act-pair · gpt-3.5-turbo

    discussions of horrific and inhumane treatment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    soType
    -0.84
     endorsements
    -0.84
     Voters
    -0.81
     Prediction
    -0.78
     Toast
    -0.76
     retweet
    -0.76
    ãĥ¤
    -0.76
    geist
    -0.75
     Carbuncle
    -0.75
     Reply
    -0.73
    POSITIVE LOGITS
     torture
    1.59
     detainees
    1.51
     prisons
    1.46
     prisoners
    1.44
     confinement
    1.41
     interrogation
    1.40
     inmates
    1.38
     prisoner
    1.37
     tortured
    1.32
     detention
    1.28
    Activations Density 0.829%

    No Known Activations