© 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. 9-RES-JB
    11. 9840
    Prev
    Next
    INDEX
    Explanations

    numerical ranges or values with a hyphen between them

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with ages, times, or distances

    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
     Lumpur
    -0.67
    querque
    -0.63
    etting
    -0.63
     Reborn
    -0.62
     Juliet
    -0.62
     Showdown
    -0.59
     Scourge
    -0.59
     Theodore
    -0.59
     Quinn
    -0.59
     Cec
    -0.59
    POSITIVE LOGITS
    something
    1.28
    odd
    1.25
    year
    1.22
    minute
    1.22
    percent
    1.21
    years
    1.17
    plus
    1.15
    hour
    1.11
    yard
    1.08
    meter
    1.06
    Activations Density 0.070%

    No Known Activations