© 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. 22159
    Prev
    Next
    INDEX
    Explanations

    words related to negative or serious situations, specifically with a grim tone

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "grim" and its variations

    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
    BU
    -0.72
    ":[
    -0.70
    ACP
    -0.70
    gdala
    -0.69
    ertodd
    -0.69
    ournals
    -0.69
    ership
    -0.69
    akeru
    -0.68
    Shares
    -0.67
    aptic
    -0.66
    POSITIVE LOGITS
    oire
    1.09
    acing
    1.03
    dark
    1.00
    ace
    0.95
     grim
    0.93
    aces
    0.93
    aced
    0.83
    lock
    0.77
    ly
    0.75
     outlook
    0.74
    Activations Density 0.015%

    No Known Activations