© 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. 0-RES-JB
    6. 15535
    Prev
    Next
    INDEX
    Explanations

    mentions of technical equipment and procedures related to work environments

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations, entities, or notable names

    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
     Pwr
    -0.89
    zed
    -0.83
    raints
    -0.78
    acular
    -0.75
    EStream
    -0.73
    ĺħ
    -0.73
    terday
    -0.73
    =-=-
    -0.72
    etheless
    -0.71
    estamp
    -0.70
    POSITIVE LOGITS
    emetery
    0.83
    mbuds
    0.82
     referen
    0.81
    senal
    0.76
    ÃįÃį
    0.75
    ometimes
    0.74
     subur
    0.72
    umenthal
    0.72
    afety
    0.71
    Nitrome
    0.70
    Activations Density 5.162%

    No Known Activations