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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14903
    Prev
    Next
    INDEX
    Explanations

    the word "carve" in various forms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the act of shaping or forming

    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
    enez
    -0.72
    REL
    -0.65
     Rutgers
    -0.64
    BUS
    -0.63
    abol
    -0.62
    COMPLE
    -0.61
     Luxem
    -0.60
    ience
    -0.60
     Kasich
    -0.60
    Princ
    -0.59
    POSITIVE LOGITS
     carving
    1.20
     carve
    1.10
     carved
    1.06
    smanship
    0.94
    tery
    0.84
     sculptures
    0.83
    cuts
    0.79
    resses
    0.78
    iffs
    0.75
    yrights
    0.74
    Activations Density 0.016%

    No Known Activations