© 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. 0-RES-JB
    11. 18100
    Prev
    Next
    INDEX
    Explanations

    verbs or nouns related to indicating, implying, or suggesting something

    oai_token-act-pair · gpt-3.5-turbo

    words related to the act of indicating or demonstrating something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Order
    -0.68
    atern
    -0.65
     Shinra
    -0.63
     XY
    -0.59
     merge
    -0.59
     erosion
    -0.58
    peg
    -0.57
    arden
    -0.57
     slide
    -0.56
    SHIP
    -0.56
    POSITIVE LOGITS
    icating
    3.50
    ications
    1.70
    icated
    1.56
    icates
    1.55
    ication
    1.34
    icative
    1.15
    icators
    1.15
    icable
    1.06
    icator
    1.01
    iating
    0.93
    Activations Density 0.014%

    No Known Activations