© 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. 4-RES-JB
    11. 17065
    Prev
    Next
    INDEX
    Explanations

    mentions of performance attributes and evaluations

    oai_token-act-pair · gpt-3.5-turbo

    references to performance metrics in various contexts

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

    No Comments

    Negative Logits
    shi
    -0.88
    yu
    -0.80
    bery
    -0.76
    yg
    -0.75
    vy
    -0.74
    Ļ½
    -0.74
    cott
    -0.73
    cot
    -0.72
    bara
    -0.70
    ke
    -0.69
    POSITIVE LOGITS
     enhancement
    0.97
     enhancing
    0.91
     tuning
    0.90
     performance
    0.89
     evaluations
    0.88
     improvement
    0.88
     optimization
    0.87
     degradation
    0.83
     evaluation
    0.83
     appraisal
    0.82
    Activations Density 0.016%

    No Known Activations