Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 18931
    Prev
    Next
    INDEX
    Explanations

    phrases indicating physical activities or locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to activities involving going out

    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
    etheless
    -0.71
    faces
    -0.70
     grids
    -0.69
    onica
    -0.66
    cells
    -0.65
    grounds
    -0.65
    ationally
    -0.65
    pires
    -0.64
    atell
    -0.63
    eki
    -0.63
    POSITIVE LOGITS
     meal
    1.02
     ride
    0.99
     session
    0.95
     haircut
    0.93
     tour
    0.89
     holiday
    0.88
     workout
    0.88
     hug
    0.87
     stroll
    0.86
     trip
    0.86
    Activations Density 0.226%

    No Known Activations