© 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. 4-RES-JB
    11. 203
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative impacts or attacks

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significant negative impacts or setbacks, specifically characterized by the word "blow."

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

    No Comments

    Negative Logits
    iosity
    -0.78
    ivan
    -0.71
    ately
    -0.68
    Govern
    -0.67
    ordan
    -0.67
    afort
    -0.66
     guiIcon
    -0.66
    natureconservancy
    -0.65
    âĸ¬
    -0.64
     Malays
    -0.62
    POSITIVE LOGITS
    hole
    0.93
     blow
    0.91
    blow
    0.91
     blows
    0.89
    outs
    0.87
    pipe
    0.85
    guns
    0.82
    out
    0.81
    hard
    0.81
    tor
    0.81
    Activations Density 0.010%

    No Known Activations