Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7026
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings or testimonies

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "testified."

    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
    ahime
    -1.06
    holy
    -0.73
    fly
    -0.71
    bidden
    -0.70
    oro
    -0.69
    alore
    -0.69
    bern
    -0.68
    scill
    -0.68
    culture
    -0.68
    flies
    -0.67
    POSITIVE LOGITS
     testimony
    1.16
     testifying
    1.11
     testimonies
    1.09
     testified
    1.08
     testify
    1.08
     witness
    0.93
     hearings
    0.93
     falsely
    0.84
     examiner
    0.84
     subpoen
    0.82
    Activations Density 0.010%

    No Known Activations