© 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. 0-RES-JB
    11. 23357
    Prev
    Next
    INDEX
    Explanations

    words related to the term "mond"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "mond"

    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
     Bleach
    -0.63
     CP
    -0.63
     INS
    -0.63
     needle
    -0.63
     abl
    -0.62
     experience
    -0.62
     tresp
    -0.62
     Zombie
    -0.61
     INV
    -0.60
     Ish
    -0.59
    POSITIVE LOGITS
    mond
    4.72
    monds
    2.41
    mons
    1.31
    mund
    1.21
    mon
    1.18
    mont
    1.15
    minster
    1.12
    mun
    1.04
    mary
    1.03
    pring
    1.02
    Activations Density 0.008%

    No Known Activations