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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8-RES-JB
    6. 61
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "concerned"

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern

    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
    avorite
    -0.77
    iller
    -0.70
    artifacts
    -0.66
    ingen
    -0.65
    ety
    -0.62
    alter
    -0.61
    apult
    -0.61
     Bom
    -0.60
    jug
    -0.60
    egal
    -0.60
    POSITIVE LOGITS
    lessly
    0.92
    ingly
    0.83
     trolling
    0.82
    ienced
    0.79
    ately
    0.78
    ativity
    0.74
    edly
    0.73
    ially
    0.71
    atives
    0.70
     bells
    0.70
    Activations Density 0.034%

    No Known Activations