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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14517
    Prev
    Next
    INDEX
    Explanations

    text related to efforts, accomplishments, and challenges in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of regaining lost status or respect

    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
    âĢ
    -1.05
    ,—
    -0.94
    .—
    -0.92
    "—
    -0.88
    —
    -0.86
    âĢķ
    -0.83
    âĸ
    -0.81
    </
    -0.81
    )—
    -0.80
    ¶
    -0.79
    POSITIVE LOGITS
     his
    0.62
     previous
    0.56
     him
    0.56
     inexper
    0.54
     reuse
    0.53
     he
    0.53
     credit
    0.53
     hindsight
    0.53
     donation
    0.52
     renovations
    0.52
    Activations Density 1.214%

    No Known Activations