© 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. 12139
    Prev
    Next
    INDEX
    Explanations

    numeric values indicating quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote a minimum quantity or threshold

    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
    Reviewer
    -0.74
    tions
    -0.72
     Dynamics
    -0.65
    selves
    -0.64
     DRAG
    -0.61
    rend
    -0.60
    ALLY
    -0.59
    bath
    -0.59
    vim
    -0.58
    ãĥ¼ãĤ¯
    -0.58
    POSITIVE LOGITS
    uner
    0.81
    foundland
    0.76
     partially
    0.71
     toler
    0.70
    egal
    0.67
    rador
    0.65
    omething
    0.65
     half
    0.64
     habitable
    0.63
     quarter
    0.63
    Activations Density 0.024%

    No Known Activations