© 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. 1-RES-JB
    11. 16387
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential danger or threats

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "rangers" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     periodic
    -0.70
    ately
    -0.68
     iron
    -0.64
    balanced
    -0.64
     Hilbert
    -0.63
    bal
    -0.63
     floor
    -0.62
    ¢
    -0.61
     earliest
    -0.60
     instantaneous
    -0.59
    POSITIVE LOGITS
    angers
    1.34
    anger
    0.96
    auga
    0.88
     unlaw
    0.86
    folk
    0.84
     behav
    0.77
     extraord
    0.76
    ocial
    0.73
    keeper
    0.72
    chwitz
    0.69
    Activations Density 0.004%

    No Known Activations