© 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. 17731
    Prev
    Next
    INDEX
    Explanations

    financial and administrative terminology

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "been."

    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
    brace
    -0.77
    join
    -0.75
     yours
    -0.72
     POW
    -0.69
    Sleep
    -0.68
    Ĥ¬
    -0.68
     mine
    -0.67
    flush
    -0.67
    fried
    -0.66
     ours
    -0.65
    POSITIVE LOGITS
    lycer
    0.75
    é¾
    0.69
     Wonders
    0.67
     Explos
    0.67
     remnants
    0.67
    acements
    0.66
    ackets
    0.66
     resemb
    0.66
    ombies
    0.65
     charms
    0.63
    Activations Density 0.000%

    No Known Activations