© 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. 9-RES-JB
    11. 15092
    Prev
    Next
    INDEX
    Explanations

    sentences or sentence fragments

    oai_token-act-pair · gpt-3.5-turbo

    references to sentences and their structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oppable
    -0.84
    jri
    -0.82
    ebus
    -0.80
    asio
    -0.80
    romeda
    -0.76
    steamapps
    -0.75
    kus
    -0.75
    OWN
    -0.75
    IED
    -0.74
    edIn
    -0.74
    POSITIVE LOGITS
     uttered
    1.10
     snippet
    0.99
     describing
    0.96
     typed
    0.95
     snippets
    0.94
     phrases
    0.93
     quotation
    0.91
     spoken
    0.89
    mith
    0.89
     highlighting
    0.87
    Activations Density 0.091%

    No Known Activations