© 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. 4145
    Prev
    Next
    INDEX
    Explanations

    instances of the word "solo" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being "solo" or alone

    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
    tics
    -0.73
     Hussain
    -0.70
    cale
    -0.69
    mosp
    -0.67
     Glover
    -0.64
     Veronica
    -0.64
    older
    -0.63
    nah
    -0.63
     Hussein
    -0.63
     CGI
    -0.63
    POSITIVE LOGITS
    iliary
    1.01
    spective
    0.83
     piano
    0.83
     ascent
    0.75
     outing
    0.75
    spection
    0.73
    ism
    0.73
    ature
    0.73
    ized
    0.73
    ilus
    0.72
    Activations Density 0.038%

    No Known Activations