© 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. 9-RES-JB
    11. 9884
    Prev
    Next
    INDEX
    Explanations

    references to the existence or non-existence of things

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to existence and knowledge over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onga
    -0.76
    ampa
    -0.70
    zees
    -0.69
    ahon
    -0.69
    ILA
    -0.65
    mi
    -0.64
    azo
    -0.63
    orio
    -0.61
    ĪĴ
    -0.60
    ems
    -0.60
    POSITIVE LOGITS
     beforehand
    1.23
     earlier
    1.20
     yesterday
    1.18
     prior
    1.17
     during
    1.14
     initially
    1.10
     until
    1.06
     before
    1.03
     originally
    0.98
     last
    0.98
    Activations Density 0.865%

    No Known Activations