© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7760
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing or planning events, actions, or topics of interest

    oai_token-act-pair · gpt-3.5-turbo

    references to film trailers and promotional media

    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
    HCR
    -0.76
    ÂŃ
    -0.71
    erenn
    -0.67
    âĢ¢
    -0.66
    </
    -0.65
    HOU
    -0.64
    ·
    -0.63
     ÂŃ
    -0.60
    oyal
    -0.59
    »
    -0.58
    POSITIVE LOGITS
     here
    1.02
     lately
    0.83
     tho
    0.82
     afterwards
    0.82
     ;)
    0.79
    ?)
    0.78
     tonight
    0.77
    ?).
    0.77
     HERE
    0.75
     tomorrow
    0.75
    Activations Density 0.691%

    No Known Activations