© 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. 7-RES-JB
    11. 23677
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical actions or movements

    oai_token-act-pair · gpt-3.5-turbo

    narrative elements related to escape or evasion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulnerability
    -0.61
    ".[
    -0.60
     guiActiveUnfocused
    -0.60
    .</
    -0.59
    [/
    -0.57
    .",
    -0.55
     [/
    -0.55
     nutshell
    -0.55
     humankind
    -0.55
    ."[
    -0.55
    POSITIVE LOGITS
     escorted
    0.68
    Lago
    0.66
    ij士
    0.63
     escort
    0.60
    ortmund
    0.58
    itely
    0.58
    Winged
    0.57
     relieved
    0.57
    Ô
    0.57
    joining
    0.56
    Activations Density 1.467%

    No Known Activations