Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16601
    Prev
    Next
    INDEX
    Explanations

    references to location specificity or the concept of local context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to levels of operation or activity within communities and organizations

    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
    ariat
    -0.67
     Nost
    -0.65
    ppe
    -0.61
     Pend
    -0.60
    THER
    -0.56
     Meter
    -0.55
     substance
    -0.53
    Staff
    -0.52
    ggles
    -0.52
     Zone
    -0.52
    POSITIVE LOGITS
    without
    0.89
    aneously
    0.89
    within
    0.82
     without
    0.80
     via
    0.79
     during
    0.75
     through
    0.75
    with
    0.74
    bnb
    0.74
     whereas
    0.74
    Activations Density 0.150%

    No Known Activations