© 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. 9-RES-JB
    11. 15992
    Prev
    Next
    INDEX
    Explanations

    dates and years in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    elements of lists or sequences, particularly dates and numerical data

    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
     evid
    -0.71
     speeches
    -0.66
     Proposition
    -0.65
     plank
    -0.64
     fathers
    -0.64
    ogy
    -0.64
     Assembly
    -0.64
     assembly
    -0.62
     duel
    -0.62
     nod
    -0.62
    POSITIVE LOGITS
    ãĤ¨ãĥ«
    1.05
    Pg
    1.02
    Flickr
    1.02
    1000
    1.01
    6000
    1.01
    oct
    1.00
    2000
    0.97
    etc
    0.95
    2003
    0.94
    OSS
    0.93
    Activations Density 0.047%

    No Known Activations