© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4175
    Prev
    Next
    INDEX
    Explanations

    locations or landmarks specifically related to water or ice

    oai_token-act-pair · gpt-3.5-turbo

    the end of sections or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     allowable
    -0.74
     coron
    -0.70
     compr
    -0.70
     physical
    -0.66
    iability
    -0.66
    enance
    -0.66
     oblig
    -0.65
     antibiotics
    -0.64
     regulators
    -0.64
    urable
    -0.64
    POSITIVE LOGITS
     Bowl
    1.14
     Creek
    1.01
     Boy
    1.00
    finger
    0.98
     Boys
    0.97
    bowl
    0.97
     Girl
    0.97
    opolis
    0.96
     Dome
    0.95
     Bunny
    0.95
    Activations Density 0.258%

    No Known Activations