© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 5756
    Prev
    Next
    INDEX
    Explanations

    phrases related to causal relationships or consequences

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating consequences or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.92
    dayName
    -0.77
    tained
    -0.74
    gie
    -0.74
    Born
    -0.72
    utenberg
    -0.71
    iece
    -0.71
    joined
    -0.70
    ãĥĩãĤ£
    -0.70
    quished
    -0.69
    POSITIVE LOGITS
     consequently
    1.40
     thereby
    1.31
     furthermore
    1.31
     moreover
    1.30
     thus
    1.27
     therefore
    1.25
     hence
    1.18
     then
    1.13
     vice
    1.13
     secondly
    1.08
    Activations Density 0.313%

    No Known Activations