© 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. 4605
    Prev
    Next
    INDEX
    Explanations

    words related to a specific ordinal position

    oai_token-act-pair · gpt-3.5-turbo

    references to "second" in various contexts or sequences

    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
    marks
    -0.72
    Magikarp
    -0.70
    roots
    -0.69
    livious
    -0.66
    vertisements
    -0.66
    WAYS
    -0.66
    bos
    -0.65
    IGHTS
    -0.65
    enne
    -0.65
    doms
    -0.65
    POSITIVE LOGITS
     installment
    1.14
     phase
    1.11
     edition
    1.07
     baseman
    1.04
     iteration
    1.02
     half
    0.97
     wave
    0.96
     tier
    0.95
     consecutive
    0.93
     quarter
    0.93
    Activations Density 0.069%

    No Known Activations