© 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. 8-RES-JB
    11. 1040
    Prev
    Next
    INDEX
    Explanations

    phrases questioning or comparing actions or choices

    oai_token-act-pair · gpt-3.5-turbo

    be verbs that question the nature or morality of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esa
    -0.69
    places
    -0.64
    aneers
    -0.64
     Working
    -0.63
     Dreams
    -0.61
     Dragonbound
    -0.61
    FTWARE
    -0.59
     Position
    -0.59
    cko
    -0.58
    irds
    -0.57
    POSITIVE LOGITS
    omorphic
    0.83
    Ļ½
    0.80
    hap
    0.78
    nt
    0.73
    gur
    0.72
    berra
    0.71
    olated
    0.68
     anybody
    0.68
    earch
    0.68
    senal
    0.65
    Activations Density 0.130%

    No Known Activations