© 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. 6-RES-JB
    11. 12761
    Prev
    Next
    INDEX
    Explanations

    keywords related to large numbers, such as "thousands" or "many"

    oai_token-act-pair · gpt-3.5-turbo

    plural nouns related to various subjects or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Relief
    -0.73
     Rapid
    -0.64
     Relations
    -0.64
     Auth
    -0.61
    cknow
    -0.61
     Redemption
    -0.60
    rison
    -0.60
     Leth
    -0.59
     Examiner
    -0.58
     Trust
    -0.58
    POSITIVE LOGITS
     imaginable
    1.02
     apiece
    0.99
     besides
    0.90
    cale
    0.88
     vying
    0.86
     including
    0.83
    uits
    0.81
    folk
    0.81
     simultaneously
    0.80
    hips
    0.79
    Activations Density 0.442%

    No Known Activations