© 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. 15892
    Prev
    Next
    INDEX
    Explanations

    numbers and structured information like dates or amounts

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers or numeric 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
    itably
    -0.73
    ivari
    -0.72
    pmwiki
    -0.70
     Lauder
    -0.70
    iating
    -0.70
    holders
    -0.68
    iator
    -0.67
    iates
    -0.66
    iations
    -0.65
     bleach
    -0.65
    POSITIVE LOGITS
    9999
    1.29
    06
    1.25
    090
    1.23
    999
    1.21
    07
    1.17
    08
    1.15
    03
    1.15
    04
    1.14
    02
    1.13
    05
    1.06
    Activations Density 0.078%

    No Known Activations