© 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. 10-RES-JB
    11. 11105
    Prev
    Next
    INDEX
    Explanations

    special characters occurring in a specific pattern

    oai_token-act-pair · gpt-3.5-turbo

    instances of numeric values or figures within the text

    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
     tremend
    -0.82
     retire
    -0.71
     princ
    -0.67
     retiring
    -0.67
     hiber
    -0.66
     veter
    -0.65
    sterdam
    -0.64
     grid
    -0.64
     Spectre
    -0.62
     hoard
    -0.61
    POSITIVE LOGITS
    Synopsis
    0.91
    isine
    0.81
    Catalog
    0.76
    Required
    0.76
    Population
    0.76
    Runtime
    0.75
    Website
    0.73
    Reviewed
    0.73
    Platform
    0.73
    اÙĦ
    0.73
    Activations Density 0.148%

    No Known Activations