© 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. 16965
    Prev
    Next
    INDEX
    Explanations

    statements made by authorities or police

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "police said," indicating reported statements or claims made by police authorities

    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
    otin
    -0.64
    Zen
    -0.63
    estern
    -0.62
    dule
    -0.60
     fixation
    -0.59
    theless
    -0.57
    ²¾
    -0.57
    bent
    -0.55
    hetical
    -0.55
    ESE
    -0.55
    POSITIVE LOGITS
    .
    0.76
    *.
    0.68
    .–
    0.62
    ummer
    0.61
     quoting
    0.60
    heit
    0.60
    Reviewer
    0.59
    urt
    0.59
    .<
    0.57
    !.
    0.56
    Activations Density 0.130%

    No Known Activations