© 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. 11-RES-JB
    11. 24406
    Prev
    Next
    INDEX
    Explanations

    words related to visual perception, perhaps with a focus on scenic or panoramic views

    oai_token-act-pair · gpt-3.5-turbo

    mentions of visual perspectives or scenes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciating
    -0.69
    ENCY
    -0.64
     McMaster
    -0.64
     isot
    -0.64
     uproar
    -0.63
    Lex
    -0.62
    vous
    -0.59
     Dent
    -0.59
    ody
    -0.59
    LES
    -0.58
    POSITIVE LOGITS
    finder
    1.55
    port
    1.32
    ports
    1.29
    points
    1.15
    point
    1.08
    ership
    1.03
     largeDownload
    1.01
    model
    0.99
    screen
    0.96
    able
    0.92
    Activations Density 0.049%

    No Known Activations