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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 645
    Prev
    Next
    INDEX
    Explanations

    information about individuals coming forward with accusations

    oai_token-act-pair · gpt-3.5-turbo

    instances of women coming forward with accusations of misconduct or abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUnfocused
    -0.82
    gob
    -0.77
    usterity
    -0.76
    peror
    -0.76
    OPA
    -0.76
    akings
    -0.74
    wich
    -0.73
     Hover
    -0.73
    ucks
    -0.72
    rador
    -0.71
    POSITIVE LOGITS
     testimonies
    1.33
     testified
    1.30
     recounted
    1.27
     testify
    1.26
     testifying
    1.22
     allegations
    1.21
     corrobor
    1.21
     allege
    1.21
     anonymously
    1.20
     accuser
    1.17
    Activations Density 0.566%

    No Known Activations