© 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. 9-RES-JB
    11. 16077
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or directives given by someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases or clauses that introduce conditions or consequences

    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
    venth
    -0.65
    chnology
    -0.63
    ²¾
    -0.63
    thora
    -0.63
    ase
    -0.62
    thia
    -0.62
    uta
    -0.62
    ãģł
    -0.61
    ¶ħ
    -0.60
     Zeal
    -0.60
    POSITIVE LOGITS
     according
    1.39
     says
    1.11
     said
    1.11
     experts
    1.08
    according
    1.04
     analysts
    0.91
     explains
    0.91
     explained
    0.90
     officials
    0.90
     writes
    0.88
    Activations Density 0.713%

    No Known Activations