© 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. 12730
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to the descriptions of things

    oai_token-act-pair · gpt-3.5-turbo

    references to items or entities that are commonly located in specific contexts or settings

    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
     Nept
    -0.61
     Mandatory
    -0.61
     SEN
    -0.59
     NCT
    -0.59
    ICO
    -0.57
    started
    -0.55
     Blaz
    -0.55
    Stats
    -0.55
     Panic
    -0.55
    adan
    -0.54
    POSITIVE LOGITS
    ered
    0.92
     elsewhere
    0.90
    ering
    0.89
    ries
    0.86
     anywhere
    0.81
    ry
    0.80
     nowhere
    0.78
    herer
    0.77
     everywhere
    0.76
     HERE
    0.76
    Activations Density 0.053%

    No Known Activations