© 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. 7-RES-JB
    11. 1697
    Prev
    Next
    INDEX
    Explanations

    numbers related to physical measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical values that represent statistics or measurements

    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
    estine
    -0.87
    bara
    -0.79
    hood
    -0.73
    scape
    -0.71
    lied
    -0.70
    wart
    -0.66
    timer
    -0.66
    alo
    -0.65
    adows
    -0.65
    sterdam
    -0.65
    POSITIVE LOGITS
    lbs
    1.01
     pounds
    1.01
     lbs
    0.96
     ILCS
    0.95
     calories
    0.95
     SHARES
    0.93
    MHz
    0.89
     kilograms
    0.88
     MHz
    0.83
    RF
    0.83
    Activations Density 0.100%

    No Known Activations