© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7474
    Prev
    Next
    INDEX
    Explanations

    character names from a specific animated show or franchise

    oai_token-act-pair · gpt-3.5-turbo

    references to characters or themes from animated series and sports players

    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
    ahime
    -0.85
    entary
    -0.76
    odo
    -0.75
    ushi
    -0.74
    opath
    -0.73
    alty
    -0.72
    ocre
    -0.71
    ates
    -0.70
    otropic
    -0.69
    atown
    -0.69
    POSITIVE LOGITS
    ially
    0.86
    cil
    0.78
    zzle
    0.74
    lies
    0.73
    velt
    0.71
    iance
    0.71
     Feather
    0.69
    pires
    0.68
    ly
    0.67
    STEM
    0.67
    Activations Density 0.133%

    No Known Activations