© 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. 23206
    Prev
    Next
    INDEX
    Explanations

    Twitter handles preceded by '@'

    oai_token-act-pair · gpt-3.5-turbo

    social media handles and user interactions

    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
     EE
    -0.81
     Tol
    -0.80
     Spac
    -0.79
     Planes
    -0.77
     aval
    -0.77
     autop
    -0.75
    Tes
    -0.74
     âĹı
    -0.74
     pestic
    -0.74
     Enchant
    -0.74
    POSITIVE LOGITS
    John
    1.73
     John
    1.70
    john
    1.56
     JOHN
    1.56
    JOHN
    1.56
     john
    1.40
     Johns
    1.39
     Johnston
    1.34
    Johnny
    1.15
     Lennon
    1.09
    Activations Density 0.227%

    No Known Activations