© 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. 11-RES-JB
    11. 16724
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making or advice-giving

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases or expressions, particularly relating to a make-or-break context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Feder
    -0.73
     Contin
    -0.65
     Chambers
    -0.65
     induction
    -0.63
     Confederation
    -0.63
     Continental
    -0.63
     Fi
    -0.62
     Cannon
    -0.62
     Peoples
    -0.61
     Rav
    -0.61
    POSITIVE LOGITS
    your
    1.57
    along
    1.24
    anything
    1.21
    everything
    1.19
    through
    1.18
    ahead
    1.18
    nothing
    1.17
    good
    1.16
    you
    1.15
    it
    1.14
    Activations Density 0.062%

    No Known Activations