© 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. 11521
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a location or position

    oai_token-act-pair · gpt-3.5-turbo

    references to vague or unspecified locations or times

    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
    ombat
    -0.79
    shock
    -0.77
    ii
    -0.76
    iframe
    -0.74
    urated
    -0.74
    icer
    -0.74
    iger
    -0.72
    andel
    -0.72
    abilities
    -0.70
    ortex
    -0.70
    POSITIVE LOGITS
     else
    1.42
    Else
    1.13
     Else
    1.04
     between
    0.98
     along
    0.95
    abouts
    0.94
     nearer
    0.92
     around
    0.91
     upstream
    0.90
     downstream
    0.88
    Activations Density 0.036%

    No Known Activations