© 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. 3-RES-JB
    11. 1859
    Prev
    Next
    INDEX
    Explanations

    keywords related to evaluating someone's or something's performance, often in a professional context

    oai_token-act-pair · gpt-3.5-turbo

    reference to performance metrics across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cot
    -0.72
    yu
    -0.69
    vy
    -0.68
    yg
    -0.66
    CU
    -0.65
    cott
    -0.65
    forward
    -0.64
    APTER
    -0.62
    ugu
    -0.61
    alone
    -0.61
    POSITIVE LOGITS
     evaluations
    1.01
     appraisal
    1.00
     audits
    0.92
     evaluation
    0.91
     enhancement
    0.82
     audit
    0.80
     improvement
    0.76
     performance
    0.76
     bonuses
    0.76
     indicators
    0.74
    Activations Density 0.025%

    No Known Activations