© 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. 6-RES-JB
    11. 11931
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "method" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to various techniques or procedures

    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
    igi
    -0.67
     Sons
    -0.66
     impression
    -0.62
     Barkley
    -0.60
     gloom
    -0.60
     Lumpur
    -0.57
    ments
    -0.56
     juven
    -0.56
     challeng
    -0.55
    owship
    -0.55
    POSITIVE LOGITS
    ologies
    1.54
    ologic
    1.14
    ologically
    1.13
    ical
    1.02
    ology
    1.02
    OLOGY
    1.02
    ically
    0.88
    sonian
    0.88
    fare
    0.85
    ologist
    0.84
    Activations Density 0.026%

    No Known Activations