© 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. 4-RES-JB
    11. 475
    Prev
    Next
    INDEX
    Explanations

    precise and accurate terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to precision and accuracy 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
    BuyableInstoreAndOnline
    -0.89
    GW
    -0.87
    swick
    -0.86
    IU
    -0.79
    imaru
    -0.72
    tha
    -0.71
    nih
    -0.69
    Lot
    -0.68
    Interstitial
    -0.68
    Connector
    -0.67
    POSITIVE LOGITS
     precision
    1.13
     calibrated
    0.91
     pinpoint
    0.88
     calibr
    0.85
     harmonic
    0.85
     compr
    0.85
    itars
    0.80
     accuracy
    0.79
    minded
    0.79
     decoding
    0.77
    Activations Density 0.009%

    No Known Activations