© 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. 2-RES-JB
    11. 3905
    Prev
    Next
    INDEX
    Explanations

    terms related to cobblestones

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "cob"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EngineDebug
    -0.73
     attm
    -0.68
     Imran
    -0.67
    variable
    -0.67
    istor
    -0.65
    Charge
    -0.65
    TPS
    -0.64
     Chronicle
    -0.63
    Princ
    -0.63
    Universal
    -0.63
    POSITIVE LOGITS
     cob
    1.15
    bled
    1.13
    bles
    1.04
    bling
    0.92
    weed
    0.91
    gob
    0.88
    anium
    0.88
    rows
    0.87
    glers
    0.85
    artisan
    0.81
    Activations Density 0.006%

    No Known Activations