© 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. 8-RES-JB
    11. 151
    Prev
    Next
    INDEX
    Explanations

    Twitter usernames starting with "No"

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "No."

    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
    iership
    -0.77
    RAFT
    -0.75
    realDonaldTrump
    -0.70
    tnc
    -0.68
    rosse
    -0.65
    worn
    -0.64
    rn
    -0.62
    hips
    -0.61
    tein
    -0.61
    lycer
    -0.61
    POSITIVE LOGITS
    zzle
    1.03
    xious
    0.99
    emi
    0.94
    isy
    0.93
    ct
    0.92
     longer
    0.91
     matter
    0.90
    ise
    0.87
    vel
    0.85
     doubt
    0.80
    Activations Density 0.066%

    No Known Activations