© 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. 18245
    Prev
    Next
    INDEX
    Explanations

    specific terms related to computer programming and software development, such as 'CLSID'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific technical identifiers or codes

    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
    wagen
    -0.70
     elector
    -0.66
    mite
    -0.62
    ifest
    -0.62
    yle
    -0.60
    ographer
    -0.59
     Harbor
    -0.59
     occupations
    -0.57
     enactment
    -0.57
    nered
    -0.57
    POSITIVE LOGITS
    ISON
    0.67
    ulhu
    0.66
    TRY
    0.65
    govtrack
    0.64
    assad
    0.64
    NRS
    0.64
    fail
    0.63
     Ow
    0.62
    ison
    0.62
     Sass
    0.62
    Activations Density 0.000%

    No Known Activations