© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 16329
    Prev
    Next
    INDEX
    Explanations

    numerical values corresponding to measurements or settings, such as sizes, lengths, limits, and thresholds

    oai_token-act-pair · gpt-3.5-turbo

    phrases regarding size and numerical limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oké
    -0.62
    aci
    -0.62
    resa
    -0.60
    izarre
    -0.58
    ibur
    -0.58
    fecture
    -0.56
    ework
    -0.56
    phabet
    -0.56
    ogie
    -0.55
    Elsewhere
    -0.55
    POSITIVE LOGITS
     5000
    1.53
     10000
    1.52
     1000
    1.49
     500
    1.45
     1024
    1.43
     4000
    1.42
     2500
    1.41
     6000
    1.40
     250
    1.39
     150
    1.39
    Activations Density 0.420%

    No Known Activations