© 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. 11-RES-JB
    11. 1422
    Prev
    Next
    INDEX
    Explanations

    phrases indicating certainty or necessity

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases and expressions of necessity or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invariably
    -1.05
     alternatively
    -1.02
     likewise
    -1.00
     inevitably
    -0.99
     doubtless
    -0.96
     presumably
    -0.95
     predictably
    -0.94
     nevertheless
    -0.92
     similarly
    -0.92
     reportedly
    -0.91
    POSITIVE LOGITS
    hing
    0.69
    ubes
    0.66
    tin
    0.66
    etsk
    0.65
    ved
    0.63
    Finish
    0.60
    hin
    0.60
    PsyNetMessage
    0.60
    ahime
    0.59
    .*
    0.59
    Activations Density 0.292%

    No Known Activations