© 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. 14859
    Prev
    Next
    INDEX
    Explanations

    emotionally charged or impactful words related to crisis or conflict

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe various qualities or conditions

    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
    claimer
    -0.84
     tremend
    -0.81
    keleton
    -0.79
    ossibility
    -0.76
    iphany
    -0.76
    ften
    -0.74
    hander
    -0.73
    asket
    -0.73
    ilege
    -0.72
    undrum
    -0.71
    POSITIVE LOGITS
     portions
    1.08
     batches
    1.01
     proportions
    0.99
     sections
    0.98
     chunks
    0.98
     venues
    0.97
     circles
    0.96
     fronts
    0.95
     tracts
    0.95
     versions
    0.94
    Activations Density 0.472%

    No Known Activations