© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 17365
    Prev
    Next
    INDEX
    Explanations

    the name "Moh" followed by varying sequences of letters and numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Moh."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istics
    -0.80
    istically
    -0.76
     laps
    -0.74
     balloons
    -0.70
     bubble
    -0.68
     balloon
    -0.67
     charms
    -0.63
     race
    -0.63
     Nept
    -0.62
    chnology
    -0.62
    POSITIVE LOGITS
    awk
    1.49
    awks
    1.28
    ammad
    1.21
    sin
    1.16
    ammed
    1.11
    atche
    1.04
    abit
    1.01
    doms
    1.00
    sen
    0.97
    aj
    0.95
    Activations Density 0.026%

    No Known Activations