© 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. 2710
    Prev
    Next
    INDEX
    Explanations

    text related to email addresses that need to be re-entered

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "re-" indicating repetition or action reversal

    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
     sqor
    -0.61
     Bord
    -0.57
     Enix
    -0.56
     Tsu
    -0.56
     dan
    -0.55
     RPGs
    -0.55
     dens
    -0.54
     shack
    -0.54
     disparate
    -0.54
    Aid
    -0.54
    POSITIVE LOGITS
    activate
    0.82
    enter
    0.82
    insert
    0.81
    Capt
    0.80
    clamation
    0.80
    valid
    0.79
    uploads
    0.79
    taboola
    0.79
    interstitial
    0.78
    submit
    0.78
    Activations Density 0.007%

    No Known Activations