© 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. 12916
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to positive attributes or recommendations

    oai_token-act-pair · gpt-3.5-turbo

    references to hidden or obscure items, often termed as "gems"

    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
    "]=>
    -0.72
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
    aos
    -0.63
    onday
    -0.63
    abama
    -0.62
    avery
    -0.62
    ploy
    -0.61
     Capacity
    -0.61
     Wage
    -0.60
    acas
    -0.59
    POSITIVE LOGITS
     obscure
    1.28
     overlooked
    1.13
     surprises
    1.12
     favorites
    1.09
     irrelevant
    1.06
     downright
    1.05
     insignificant
    1.03
     lesser
    1.02
     unexpected
    1.02
     unrelated
    1.01
    Activations Density 0.552%

    No Known Activations