© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 14185
    Prev
    Next
    INDEX
    Explanations

    references to "PI" or "pi" in a tech or numeric context

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific product or brand within a technical or promotional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ding
    -0.93
    */(
    -0.89
    suit
    -0.88
    sound
    -0.79
    space
    -0.78
    suits
    -0.77
    spread
    -0.76
    comes
    -0.76
    speed
    -0.74
    sword
    -0.74
    POSITIVE LOGITS
    PI
    1.22
    ZZ
    0.90
    OGR
    0.85
    HK
    0.85
    PLA
    0.84
     PI
    0.81
    KA
    0.81
    PS
    0.79
    agos
    0.77
    KE
    0.76
    Activations Density 0.007%

    No Known Activations