© 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. 9-RES-JB
    11. 18042
    Prev
    Next
    INDEX
    Explanations

    numerical values such as '2', '3', and '8'

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and references to processes related to measurement or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ga
    -0.65
     airs
    -0.62
     Chatt
    -0.62
     Schne
    -0.60
     Init
    -0.60
     Reneg
    -0.60
    agra
    -0.57
     Moj
    -0.56
    alach
    -0.56
     GTA
    -0.56
    POSITIVE LOGITS
    )
    0.93
    ++)
    0.84
    )...
    0.73
    )(
    0.72
    ods
    0.72
     worms
    0.72
    /)
    0.71
    )'
    0.71
    -)
    0.69
    ï¸ı
    0.69
    Activations Density 0.090%

    No Known Activations