© 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. 11-RES-JB
    11. 12557
    Prev
    Next
    INDEX
    Explanations

    specific numerical values in a format of 9, followed by another digit

    oai_token-act-pair · gpt-3.5-turbo

    references to firearms and ammunition specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stood
    -0.81
    iates
    -0.74
    iated
    -0.73
    iating
    -0.67
    lie
    -0.67
    iator
    -0.66
    pmwiki
    -0.65
    ivari
    -0.63
    itably
    -0.63
    enture
    -0.63
    POSITIVE LOGITS
    9999
    1.38
    999
    1.30
    090
    1.30
    06
    1.23
    07
    1.20
    02
    1.19
    03
    1.18
    08
    1.17
    04
    1.16
    05
    1.13
    Activations Density 0.061%

    No Known Activations