© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3086
    Prev
    Next
    INDEX
    Explanations

    feedback-related content, including reports, listener feedback, and engagement with the community

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to community feedback and engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    wikipedia
    -0.79
    çĶ°
    -0.65
    esm
    -0.63
     kidnap
    -0.62
     abduction
    -0.62
    WithNo
    -0.61
    leck
    -0.60
    ikuman
    -0.60
    bold
    -0.60
     Canaver
    -0.59
    POSITIVE LOGITS
     feedback
    1.24
     Feedback
    1.17
     constructive
    0.96
     loops
    0.89
     appreciated
    0.87
     testers
    0.83
     Emails
    0.82
     welcome
    0.81
     suggestions
    0.81
     emails
    0.80
    Activations Density 0.175%

    No Known Activations