© 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. 7-RES-JB
    11. 1589
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and choices

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "go with" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stem
    -0.83
    pring
    -0.79
    bugs
    -0.75
    affected
    -0.72
    undo
    -0.72
    Released
    -0.72
    clips
    -0.71
    taboola
    -0.69
    wordpress
    -0.68
    dep
    -0.67
    POSITIVE LOGITS
     whichever
    0.83
    EStream
    0.78
     precaution
    0.76
    raviolet
    0.73
     impunity
    0.71
     whatever
    0.71
    ramid
    0.71
     bandwagon
    0.70
     blindly
    0.69
    «ĺ
    0.69
    Activations Density 0.032%

    No Known Activations