© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 16067
    Prev
    Next
    INDEX
    Explanations

    references to bats and related actions or objects

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "bat" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LV
    -0.68
    éĸ
    -0.65
    zanne
    -0.63
    eous
    -0.61
    mble
    -0.60
    naire
    -0.59
    xia
    -0.59
    taining
    -0.59
     SPACE
    -0.57
    ately
    -0.57
    POSITIVE LOGITS
    tered
    1.22
    allion
    1.15
    avia
    1.07
    hing
    1.01
    ched
    0.96
    iatus
    0.96
    cher
    0.95
    tell
    0.94
    ches
    0.94
    chers
    0.93
    Activations Density 0.030%

    No Known Activations