© 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. 10534
    Prev
    Next
    INDEX
    Explanations

    references to specific names mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals and their affiliations or actions

    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
    cas
    -0.73
     Malays
    -0.72
    ahi
    -0.70
    plates
    -0.64
    tered
    -0.64
    ļé
    -0.63
    teenth
    -0.63
    rav
    -0.62
    anguages
    -0.59
    thood
    -0.59
    POSITIVE LOGITS
    agan
    0.80
     Router
    0.80
    nor
    0.80
    ceived
    0.73
    INGTON
    0.70
    uther
    0.69
    actor
    0.69
    actions
    0.68
    ally
    0.67
    burgh
    0.67
    Activations Density 0.086%

    No Known Activations