© 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. 8-RES-JB
    11. 18473
    Prev
    Next
    INDEX
    Explanations

    strong, critical adjectives or phrases

    oai_token-act-pair · gpt-3.5-turbo

    emotionally charged adjectives that convey strong criticism or commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hops
    -0.95
    qqa
    -0.81
    gat
    -0.78
    slave
    -0.77
    cells
    -0.76
    ween
    -0.76
    chwitz
    -0.73
    plane
    -0.73
    Jump
    -0.71
     Stores
    -0.70
    POSITIVE LOGITS
     commentary
    1.29
     rebuke
    1.23
     indictment
    1.23
     critique
    1.20
     rebutt
    1.19
     understatement
    1.16
     remarks
    1.14
     statement
    1.14
     conclusion
    1.11
     explanation
    1.08
    Activations Density 0.233%

    No Known Activations