© 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. 1-RES-JB
    11. 3627
    Prev
    Next
    INDEX
    Explanations

    references to strongly encouraging or advising action

    oai_token-act-pair · gpt-3.5-turbo

    expressions of urging or encouraging action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icators
    -0.82
     Surv
    -0.78
    icator
    -0.75
    missions
    -0.70
     Half
    -0.68
    ammy
    -0.67
    poon
    -0.64
    integ
    -0.63
    ded
    -0.63
    este
    -0.63
    POSITIVE LOGITS
     urge
    1.36
     urges
    1.07
     incent
    0.99
    ĸļ
    0.81
     urging
    0.78
    ingly
    0.77
     reminding
    0.75
     urged
    0.72
     compel
    0.71
     tempted
    0.71
    Activations Density 0.006%

    No Known Activations