© 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. 20472
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express uncertainty or conditionality

    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
     To
    -0.53
     to
    -0.50
     Demand
    -0.46
    to
    -0.43
     TO
    -0.41
     Wonderful
    -0.41
    ombo
    -0.40
     Seeking
    -0.40
     Quant
    -0.39
     Celebr
    -0.39
    POSITIVE LOGITS
    none
    0.61
    although
    0.60
    only
    0.59
    albeit
    0.59
     only
    0.56
    without
    0.56
    though
    0.56
    even
    0.55
    yond
    0.54
    but
    0.54
    Activations Density 1.419%

    No Known Activations