© 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. 4-RES-JB
    11. 15705
    Prev
    Next
    INDEX
    Explanations

    places or entities named "Ant" followed by a number or other word

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "Ant" in various contexts

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

    No Comments

    Negative Logits
    UTION
    -1.02
    FORMATION
    -0.81
    ESSION
    -0.79
    OURCE
    -0.75
    UGE
    -0.74
    OUP
    -0.73
    )=(
    -0.71
    wagen
    -0.69
     Stras
    -0.69
    ETS
    -0.67
    POSITIVE LOGITS
    oine
    1.12
    enna
    1.02
    elope
    1.02
    acid
    1.00
    agonists
    0.99
    ioch
    0.97
    rop
    0.96
    agonist
    0.96
    idepress
    0.95
    onym
    0.94
    Activations Density 0.012%

    No Known Activations