© 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. 7-RES-JB
    11. 6414
    Prev
    Next
    INDEX
    Explanations

    words related to being concerned or worried about something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern regarding various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingen
    -0.74
    ingers
    -0.73
    iller
    -0.71
    arb
    -0.69
    artifacts
    -0.66
    buff
    -0.66
    ety
    -0.65
    avorite
    -0.64
    forms
    -0.64
    ete
    -0.62
    POSITIVE LOGITS
    lessly
    0.92
     trolling
    0.83
    reon
    0.80
    wart
    0.74
    ingly
    0.74
    ienced
    0.74
    edly
    0.72
    iously
    0.70
    warts
    0.69
    enza
    0.67
    Activations Density 0.029%

    No Known Activations