© 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. 2-RES-JB
    11. 9005
    Prev
    Next
    INDEX
    Explanations

    names of specific places or entities

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the letter "O" as a standalone character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cures
    -0.80
    aughed
    -0.77
     curing
    -0.77
    sembly
    -0.73
     tackling
    -0.67
     touring
    -0.66
     cure
    -0.65
     electrodes
    -0.65
    anwhile
    -0.64
    nown
    -0.63
    POSITIVE LOGITS
    ://
    0.69
    rior
    0.69
    ONSORED
    0.68
    book
    0.67
    force
    0.67
     2048
    0.66
    fml
    0.65
    hered
    0.64
    trust
    0.62
    keeping
    0.62
    Activations Density 0.000%

    No Known Activations