© 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. 8-RES-JB
    11. 2507
    Prev
    Next
    INDEX
    Explanations

    steps or instructions within a process

    oai_token-act-pair · gpt-3.5-turbo

    steps or instructions in a procedural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pengu
    -0.80
    ãĥīãĥ©ãĤ´ãĥ³
    -0.71
    eatures
    -0.69
    ruciating
    -0.69
     Unic
    -0.69
    ãĥ©ãĥ³
    -0.67
    ciating
    -0.66
    gdala
    -0.66
    NetMessage
    -0.66
    inately
    -0.66
    POSITIVE LOGITS
    hens
    1.09
    Step
    0.93
    dad
    0.91
    hen
    0.88
    daughter
    0.86
    antry
    0.85
    isters
    0.84
    hent
    0.84
    sis
    0.83
    steps
    0.82
    Activations Density 0.033%

    No Known Activations