© 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. 7058
    Prev
    Next
    INDEX
    Explanations

    words related to specific physical objects or substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to materials and substances, particularly in scientific 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
    ctor
    -0.72
    TI
    -0.70
    ALLY
    -0.69
     ethic
    -0.66
    Leader
    -0.63
     VID
    -0.63
    Work
    -0.63
    ctors
    -0.63
    OWN
    -0.62
    Student
    -0.62
    POSITIVE LOGITS
    mith
    1.32
    ynthesis
    1.16
    hips
    1.15
    poons
    1.14
    heet
    1.11
    pring
    1.10
    peed
    1.06
    hops
    1.05
    terday
    1.04
    uits
    1.04
    Activations Density 0.146%

    No Known Activations