© 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. 0-RES-JB
    11. 1534
    Prev
    Next
    INDEX
    Explanations

    instances related to the initial phase or starting point of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to introductory or preliminary stages

    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
     Dame
    -0.73
     ..."
    -0.69
    greg
    -0.65
    scribe
    -0.64
     haun
    -0.64
     SPORTS
    -0.63
    stained
    -0.63
     Journalists
    -0.63
    well
    -0.63
    steen
    -0.63
    POSITIVE LOGITS
     initial
    3.40
    initial
    2.43
    Initial
    2.28
     Initial
    2.18
     initially
    1.84
     preliminary
    1.64
     initialization
    1.49
     original
    1.48
     immediate
    1.36
     initialize
    1.33
    Activations Density 0.012%

    No Known Activations