© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 6247
    Prev
    Next
    INDEX
    Explanations

    instances of the word "inform" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "inform" in various contexts

    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
    Kings
    -0.71
    âĻ¥
    -0.66
    imposed
    -0.65
    á
    -0.63
     vain
    -0.62
    cdn
    -0.62
    FUN
    -0.61
     Kings
    -0.61
    DAY
    -0.60
    mad
    -0.60
    POSITIVE LOGITS
    ally
    1.09
    tale
    0.97
    ations
    0.89
    ificantly
    0.86
    ingly
    0.85
    acion
    0.85
     inform
    0.83
    ational
    0.80
    osc
    0.79
    ographics
    0.78
    Activations Density 0.014%

    No Known Activations