© 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. 0-RES-JB
    11. 16931
    Prev
    Next
    INDEX
    Explanations

    adjectives related to the intensity or extremity of a situation

    oai_token-act-pair · gpt-3.5-turbo

    the word "severe" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lobby
    -0.76
     Caf
    -0.74
    antry
    -0.72
    lad
    -0.67
    ity
    -0.67
    andowski
    -0.67
     Illum
    -0.66
    elle
    -0.64
    izzle
    -0.64
    istas
    -0.63
    POSITIVE LOGITS
     severe
    3.12
    severe
    2.06
     severity
    1.82
     serious
    1.78
     severely
    1.76
     crippling
    1.65
     extreme
    1.64
     debilitating
    1.63
     drastic
    1.59
     mild
    1.58
    Activations Density 0.018%

    No Known Activations