© 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. 14716
    Prev
    Next
    INDEX
    Explanations

    mention of past actions or hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal agency and responsibility

    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
    izens
    -0.65
     quirks
    -0.65
     Bits
    -0.63
    BUG
    -0.62
     Colleges
    -0.61
     freezes
    -0.60
     loops
    -0.60
     themselves
    -0.59
     Lovecraft
    -0.59
     seams
    -0.59
    POSITIVE LOGITS
     myself
    1.40
     personally
    0.98
     âĢ¦"
    0.87
     my
    0.80
    displayText
    0.75
     ministerial
    0.75
     sworn
    0.74
    %"
    0.73
    chair
    0.72
     privileged
    0.72
    Activations Density 0.760%

    No Known Activations