© 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. 11-RES-JB
    11. 19322
    Prev
    Next
    INDEX
    Explanations

    prices or cost-related information

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and terms related to measurement over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Obj
    -0.68
    æ©
    -0.67
    borgh
    -0.66
    enance
    -0.64
    nikov
    -0.64
     Adin
    -0.64
    igs
    -0.64
     artif
    -0.63
    igraph
    -0.63
     Creed
    -0.62
    POSITIVE LOGITS
    month
    1.38
     month
    1.37
     months
    1.35
    months
    1.30
     Month
    1.26
    Month
    1.21
     Months
    1.18
     monthly
    0.98
     Monthly
    0.94
    soDeliveryDate
    0.83
    Activations Density 0.029%

    No Known Activations