© 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. 8-RES-JB
    11. 10248
    Prev
    Next
    INDEX
    Explanations

    the specific string "Q9"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the letter 'Q'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagen
    -0.84
     Lauder
    -0.68
     Awakens
    -0.67
    fulness
    -0.66
    ufact
    -0.66
     Nadu
    -0.66
     readable
    -0.63
     Painter
    -0.61
    fitting
    -0.60
     Proc
    -0.60
    POSITIVE LOGITS
    UE
    1.16
    ues
    1.13
    ued
    1.08
    ubes
    1.05
    addafi
    1.03
    WER
    1.01
    atari
    0.97
    atar
    0.97
    LD
    0.96
    iu
    0.94
    Activations Density 0.028%

    No Known Activations