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

    Neuronpedia

    Jacobian LensNEW
    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. 20558
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific unicode characters

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases indicating disagreement

    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
     Gaul
    -0.65
     jog
    -0.65
     sacrific
    -0.62
     blitz
    -0.57
     Allies
    -0.56
     capsule
    -0.56
     Stats
    -0.55
     Britons
    -0.55
     looms
    -0.55
     fumble
    -0.55
    POSITIVE LOGITS
    tre
    0.91
    ï¸ı
    0.89
    vable
    0.81
    forth
    0.76
    tu
    0.75
    emb
    0.75
    ulty
    0.75
    vent
    0.74
    yet
    0.74
    minent
    0.74
    Activations Density 0.135%

    No Known Activations