© 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. 4455
    Prev
    Next
    INDEX
    Explanations

    numbers representing quantities in the hundreds

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly those representing large quantities

    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
    ronic
    -0.73
    hold
    -0.72
    doms
    -0.71
    actic
    -0.71
    colm
    -0.70
    inion
    -0.70
    oles
    -0.69
    ramid
    -0.69
    kell
    -0.69
    isen
    -0.68
    POSITIVE LOGITS
     watts
    0.86
     MHz
    0.84
     milliseconds
    0.83
     metres
    0.82
     acres
    0.80
    px
    0.80
    Hz
    0.79
     pounds
    0.79
     ponies
    0.78
     000
    0.77
    Activations Density 0.063%

    No Known Activations