© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 10676
    Prev
    Next
    INDEX
    Explanations

    terms related to software and project management processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to management and analysis within various utility functions

    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
    ewitness
    -0.87
    urnal
    -0.86
    ometown
    -0.78
    zl
    -0.78
    birth
    -0.75
    ãĥĥãĥī
    -0.75
    bid
    -0.69
    ãĥĺãĥ©
    -0.69
    ighth
    -0.69
    é¾įåĸļ士
    -0.69
    POSITIVE LOGITS
     algorithms
    1.20
     techniques
    1.18
     tools
    1.16
     software
    1.15
     tool
    1.15
     algorithm
    1.10
     capabilities
    1.09
     technique
    1.07
     capability
    1.03
     routines
    1.01
    Activations Density 0.265%

    No Known Activations