© 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. 0-RES-JB
    11. 1976
    Prev
    Next
    INDEX
    Explanations

    phrases related to quick and urgent actions or responses

    oai_token-act-pair · gpt-3.5-turbo

    words relating to urgent or chaotic actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Innocent
    -0.76
    OF
    -0.72
     Eth
    -0.68
     Prest
    -0.68
     Bonds
    -0.67
     perf
    -0.67
     Wind
    -0.65
    gas
    -0.65
     LW
    -0.65
    orthy
    -0.62
    POSITIVE LOGITS
     scramble
    3.59
     scrambling
    3.22
     scrambled
    3.16
     scram
    2.93
     shuffle
    1.19
     scr
    1.06
     casc
    1.04
     shuff
    1.03
     cascade
    1.02
     frantically
    1.00
    Activations Density 0.019%

    No Known Activations