© 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. 1-RES-JB
    11. 24245
    Prev
    Next
    INDEX
    Explanations

    Roman numerals followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to "IX" and related context within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    collection
    -0.75
    isman
    -0.72
    kson
    -0.67
     Haku
    -0.66
    rill
    -0.61
    offer
    -0.61
    actor
    -0.61
    aff
    -0.60
    mot
    -0.60
    ischer
    -0.59
    POSITIVE LOGITS
    IX
    1.33
    TERN
    0.94
    CEPT
    0.84
    DAQ
    0.83
    CLUS
    0.82
    daq
    0.79
    atile
    0.79
    BSD
    0.79
    edIn
    0.79
    alde
    0.78
    Activations Density 0.005%

    No Known Activations