© 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. 2188
    Prev
    Next
    INDEX
    Explanations

    situations where certain actions or conditions lead to specific outcomes

    oai_token-act-pair · gpt-3.5-turbo

    the repeated usage of the phrase "be it" in various contexts

    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
    SPONSORED
    -0.83
    ilib
    -0.80
    idates
    -0.72
    uda
    -0.68
    ogun
    -0.67
    inav
    -0.66
    redit
    -0.66
    ersen
    -0.65
    edit
    -0.64
    "},
    -0.62
    POSITIVE LOGITS
     intentional
    0.68
     raining
    0.63
     EntityItem
    0.61
    audi
    0.59
     classroom
    0.59
     contemplating
    0.58
    LOD
    0.58
     physical
    0.58
     ç¥ŀ
    0.56
     geography
    0.54
    Activations Density 0.167%

    No Known Activations