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

    words related to confusion or mixed signals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "confide" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izons
    -0.77
    senal
    -0.76
    ©¶æ
    -0.75
    Ô
    -0.71
    DAY
    -0.68
     Kinnikuman
    -0.66
    GY
    -0.65
    chnology
    -0.65
    GET
    -0.64
    NING
    -0.64
    POSITIVE LOGITS
    ederation
    1.03
     conf
    1.01
    luence
    0.93
    eree
    0.88
    essional
    0.88
    licted
    0.85
    usional
    0.82
    usions
    0.81
    eder
    0.80
    erences
    0.76
    Activations Density 0.006%

    No Known Activations