© 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. 11-RES-JB
    11. 7580
    Prev
    Next
    INDEX
    Explanations

    numbers relating to measurements or quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly those related to measurements or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hunt
    -0.66
    warts
    -0.65
    atories
    -0.65
    ror
    -0.61
    croft
    -0.60
     arsen
    -0.59
    frames
    -0.58
    erville
    -0.58
    anced
    -0.56
    ailed
    -0.56
    POSITIVE LOGITS
    mAh
    1.28
    MHz
    1.18
     MHz
    1.10
    mL
    1.07
    px
    1.07
    cc
    0.99
     ILCS
    0.98
    mA
    0.97
    ml
    0.97
    rpm
    0.95
    Activations Density 0.117%

    No Known Activations