© 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. 8-RES-JB
    11. 2485
    Prev
    Next
    INDEX
    Explanations

    phrases related to a movement or a journey in a physical or metaphorical sense

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "way" or pathways in various contexts

    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
     Plex
    -0.73
    nect
    -0.71
    oubted
    -0.67
    ishable
    -0.66
    uster
    -0.66
    cius
    -0.66
    ifer
    -0.63
    ãĥĩãĤ£
    -0.62
    vae
    -0.62
    icio
    -0.62
    POSITIVE LOGITS
    ward
    0.83
     toward
    0.78
    seeing
    0.75
    WARD
    0.74
    finding
    0.73
     to
    0.72
     home
    0.72
    finder
    0.71
    fare
    0.68
     towards
    0.67
    Activations Density 0.037%

    No Known Activations