© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20579
    Prev
    Next
    INDEX
    Explanations

    mentions of materials or substances, particularly those related to specific features or locations.

    oai_token-act-pair · gpt-3.5-turbo

    terms related to materials and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UNCH
    -0.77
    ctor
    -0.68
    astern
    -0.66
    ELF
    -0.63
    pport
    -0.63
    outhern
    -0.63
    ected
    -0.62
    XT
    -0.61
    ASED
    -0.60
    IRO
    -0.59
    POSITIVE LOGITS
    s
    2.88
    sburg
    1.67
    sie
    1.51
    ski
    1.44
    sb
    1.43
    sburgh
    1.40
    sis
    1.34
    sf
    1.34
    sg
    1.31
    sch
    1.31
    Activations Density 0.565%

    No Known Activations