© 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. 3-RES-JB
    6. 23042
    Prev
    Next
    INDEX
    Explanations

    terms related to validating or validation processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to validation processes and statistical verification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bill
    -0.80
    eworld
    -0.78
    bestos
    -0.74
    Ill
    -0.74
    hunt
    -0.70
    bors
    -0.69
     Rove
    -0.68
    ulhu
    -0.67
    é¾įåĸļ士
    -0.65
    hani
    -0.65
    POSITIVE LOGITS
     validation
    0.93
    idated
    0.83
     validate
    0.79
    idation
    0.76
     Testing
    0.74
     validated
    0.74
    aution
    0.72
    orously
    0.71
     testing
    0.68
     Seym
    0.67
    Activations Density 0.013%

    No Known Activations