© 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. 18577
    Prev
    Next
    INDEX
    Explanations

    words related to feathers and claws

    oai_token-act-pair · gpt-3.5-turbo

    terms related to animal appendages and fire imagery

    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
    minist
    -0.77
    nce
    -0.73
    iazep
    -0.73
     Physicians
    -0.72
    League
    -0.70
    vent
    -0.70
    anan
    -0.69
    lich
    -0.68
    medi
    -0.68
     Galile
    -0.67
    POSITIVE LOGITS
    mith
    1.44
    hops
    1.40
    heet
    1.28
    uits
    1.26
    hips
    1.18
    hip
    1.13
    ynthesis
    1.09
    cale
    1.08
    hirt
    1.08
    paces
    1.07
    Activations Density 0.028%

    No Known Activations