© 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. 6-RES-JB
    11. 7045
    Prev
    Next
    INDEX
    Explanations

    instances of removal or expulsion of individuals from various roles or positions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to removal or expulsion from positions or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ratulations
    -0.82
    ascript
    -0.81
    ecd
    -0.80
    BUG
    -0.75
    sylv
    -0.73
    cule
    -0.73
    retty
    -0.72
    lopp
    -0.72
    uid
    -0.71
    culosis
    -0.70
    POSITIVE LOGITS
     Vietnam
    0.76
     Paradise
    0.76
     captivity
    0.75
     orbit
    0.74
     Olympus
    0.72
     premises
    0.72
     obscurity
    0.72
     Valhalla
    0.70
     existence
    0.70
     Tasmania
    0.70
    Activations Density 0.093%

    No Known Activations