© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 24166
    Prev
    Next
    INDEX
    Explanations

    dotted patterns or visual elements

    oai_token-act-pair · gpt-3.5-turbo

    patterns related to dotted or dotted lines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.76
    CVE
    -0.73
    ðĿ
    -0.71
    è£ħ
    -0.65
    Represent
    -0.65
    Asset
    -0.62
    PLIED
    -0.62
    Whit
    -0.61
     includ
    -0.60
    nesota
    -0.60
    POSITIVE LOGITS
    otted
    1.14
    kered
    1.03
    swick
    0.95
    nikov
    0.83
    chio
    0.83
    ronics
    0.77
    cules
    0.74
     IMAGES
    0.74
    miah
    0.74
    ovo
    0.73
    Activations Density 0.010%

    No Known Activations