© 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. 3-RES-JB
    11. 13584
    Prev
    Next
    INDEX
    Explanations

    terms related to improvement

    oai_token-act-pair · gpt-3.5-turbo

    fragments or variations of the word "improve" and its related meanings

    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
    NetMessage
    -0.91
    DragonMagazine
    -0.84
     è£ıè
    -0.78
     guiActiveUnfocused
    -0.74
    RH
    -0.69
    channelAvailability
    -0.68
     Lutheran
    -0.67
     dinosaurs
    -0.67
    REDACTED
    -0.67
     Danish
    -0.66
    POSITIVE LOGITS
    ving
    1.17
    bable
    1.14
    bably
    1.13
    vers
    1.04
    ple
    1.02
    per
    1.00
    bers
    0.98
    bled
    0.97
    pering
    0.96
    ved
    0.94
    Activations Density 0.008%

    No Known Activations