© 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. 6-RES-JB
    11. 2972
    Prev
    Next
    INDEX
    Explanations

    keywords indicating a current timeframe or situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "for now"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammy
    -0.74
    ashtra
    -0.64
    vironments
    -0.64
    ved
    -0.64
    adr
    -0.63
    qqa
    -0.62
    azeera
    -0.62
    assic
    -0.61
    sbm
    -0.60
    resa
    -0.60
    POSITIVE LOGITS
    adays
    0.83
    here
    0.82
     sake
    0.82
     though
    0.74
     anyway
    0.71
    rief
    0.70
     undisclosed
    0.69
     undecided
    0.68
     Idol
    0.68
     purposes
    0.66
    Activations Density 0.018%

    No Known Activations