© 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. 5773
    Prev
    Next
    INDEX
    Explanations

    words containing the substring "ble."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "bl" in various contexts

    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
     Dangerous
    -0.68
     Situation
    -0.68
     Robots
    -0.64
     Gund
    -0.63
     Tags
    -0.63
     Occupations
    -0.63
    mble
    -0.62
    HER
    -0.62
    eers
    -0.62
    LER
    -0.61
    POSITIVE LOGITS
    anches
    1.12
    anche
    1.11
    estone
    1.06
    ossom
    1.04
    adders
    1.02
    aded
    0.98
    adder
    0.98
    ight
    0.98
    acks
    0.97
    anch
    0.95
    Activations Density 0.010%

    No Known Activations