© 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. 5773
    Prev
    Next
    INDEX
    Explanations

    connections or conjunctions that suggest relationships or lists of examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    information related to current events or news

    oai_token-act-pair · gpt-3.5-turbo
    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
    onia
    -0.76
    amar
    -0.71
    ãĥĨãĤ£
    -0.70
    ãĥ¼ãĥ
    -0.67
    umat
    -0.66
    ãĥŁ
    -0.66
    Lic
    -0.64
    ãĤ¤
    -0.64
    ergic
    -0.63
    eg
    -0.62
    POSITIVE LOGITS
     how
    1.39
     why
    1.22
     whether
    1.04
    why
    1.03
     discusses
    0.99
     pitfalls
    0.98
     motivations
    0.98
     WHY
    0.97
     compares
    0.93
     implications
    0.91
    Activations Density 0.353%

    No Known Activations