© 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. 7776
    Prev
    Next
    INDEX
    Explanations

    phrases indicating following a lead or example, or imitating a course of action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "follow suit" and related concepts of conformity and alignment

    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
    ricted
    -0.67
    akin
    -0.65
    finished
    -0.65
     peanuts
    -0.64
    lav
    -0.63
    erved
    -0.60
     Osc
    -0.60
     Serving
    -0.59
    anon
    -0.57
     Avenger
    -0.56
    POSITIVE LOGITS
     srfAttach
    0.76
    FontSize
    0.73
    à¥
    0.73
    ALSE
    0.72
    ername
    0.72
    Route
    0.70
    ée
    0.69
    ":[
    0.69
    ÃĽ
    0.68
    chnology
    0.67
    Activations Density 0.064%

    No Known Activations