© 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. 6-RES-JB
    11. 12112
    Prev
    Next
    INDEX
    Explanations

    instances of the word "feedback" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to user feedback and responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neys
    -0.84
    asar
    -0.76
    chin
    -0.74
    annis
    -0.73
    bold
    -0.70
    amina
    -0.69
    wikipedia
    -0.68
    adem
    -0.68
    Dial
    -0.67
    ffe
    -0.66
    POSITIVE LOGITS
     feedback
    1.18
     testers
    0.97
     loops
    0.96
     Feedback
    0.96
     assurance
    0.79
     loop
    0.79
    ible
    0.77
     reviewers
    0.71
     reinforcement
    0.69
    storms
    0.67
    Activations Density 0.041%

    No Known Activations