© 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. 8-RES-JB
    11. 6402
    Prev
    Next
    INDEX
    Explanations

    numbers indicating a minimum quantity of people or things involved in an event

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating casualty counts or minimum numbers in contexts related to incidents or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taboola
    -0.87
    SourceFile
    -0.70
    tions
    -0.67
    gars
    -0.66
    kai
    -0.63
    âĵĺ
    -0.61
    tyard
    -0.61
    ggles
    -0.60
    ãĤ¿
    -0.59
    ohydrate
    -0.59
    POSITIVE LOGITS
     eight
    0.78
     nine
    0.76
    eight
    0.76
     six
    0.75
     five
    0.74
     four
    0.74
     seven
    0.73
    six
    0.73
     129
    0.71
     three
    0.71
    Activations Density 0.026%

    No Known Activations