© 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. 11-RES-JB
    11. 1785
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing detailed descriptions or insights

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a detailed account or analysis of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alone
    -0.65
    EEP
    -0.63
    soever
    -0.62
    Pg
    -0.61
    iki
    -0.60
    ctory
    -0.59
    OGR
    -0.59
    ICT
    -0.58
    ngth
    -0.58
    BSD
    -0.58
    POSITIVE LOGITS
     how
    1.65
     why
    1.55
     what
    1.33
     WHY
    1.22
     whence
    1.19
     whats
    1.18
    why
    1.17
    how
    1.09
     where
    1.06
     whether
    1.05
    Activations Density 0.356%

    No Known Activations