© 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. 11-RES-JB
    11. 18846
    Prev
    Next
    INDEX
    Explanations

    documents that have been released

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite article "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fights
    -0.73
    cells
    -0.70
     eyed
    -0.68
     mills
    -0.67
     establishments
    -0.67
    bars
    -0.67
     è£ıè
    -0.67
    things
    -0.66
    Allow
    -0.66
    ees
    -0.65
    POSITIVE LOGITS
     slew
    1.15
     scathing
    1.06
     lengthy
    1.03
     series
    1.03
     plethora
    1.02
     flurry
    0.97
     blister
    0.95
     damning
    0.95
     trove
    0.95
     whopping
    0.94
    Activations Density 0.203%

    No Known Activations