© 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. 10816
    Prev
    Next
    INDEX
    Explanations

    keywords related to descriptions of objects or entities that are in a state of disrepair

    oai_token-act-pair · gpt-3.5-turbo

    empty tokens or sections in the text

    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
    overs
    -0.47
    Aren
    -0.46
    AUD
    -0.46
    Events
    -0.46
    sheets
    -0.45
    En
    -0.44
    eworks
    -0.44
    outs
    -0.44
    aways
    -0.44
     besides
    -0.44
    POSITIVE LOGITS
     lot
    0.58
     bunch
    0.56
    venge
    0.55
    usterity
    0.55
    uras
    0.54
    versive
    0.53
    sexual
    0.52
     comma
    0.51
     prostitute
    0.51
     nutshell
    0.51
    Activations Density 0.566%

    No Known Activations