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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16260
    Prev
    Next
    INDEX
    Explanations

    words related to allegations and instances of sexual misconduct

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sexual misconduct and allegations against individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REE
    -0.84
     guiActiveUnfocused
    -0.78
    rious
    -0.75
    eric
    -0.75
    AY
    -0.72
    OTAL
    -0.72
    OTS
    -0.71
    ernel
    -0.71
    HCR
    -0.70
    ROM
    -0.70
    POSITIVE LOGITS
     accuser
    1.30
     allegations
    1.23
     allegation
    1.05
    Sexual
    1.00
     abuser
    0.97
     accusations
    0.96
     abusers
    0.95
     sexually
    0.95
     complainant
    0.94
     rape
    0.91
    Activations Density 0.128%

    No Known Activations