© 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. 3-RES-JB
    11. 13004
    Prev
    Next
    INDEX
    Explanations

    words related to charity or help

    oai_token-act-pair · gpt-3.5-turbo

    the word "cares" 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
    UE
    -0.78
    Assembly
    -0.68
    ured
    -0.63
    ELD
    -0.61
    IME
    -0.61
    OOL
    -0.60
     ow
    -0.60
    REE
    -0.59
     Hudson
    -0.59
    allery
    -0.58
    POSITIVE LOGITS
    pace
    0.95
    tsky
    0.92
    aurus
    0.89
    cue
    0.88
    pite
    0.83
    bian
    0.81
    cale
    0.78
    amples
    0.77
    ares
    0.77
    jon
    0.77
    Activations Density 0.006%

    No Known Activations