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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 0-RES-JB
    6. 23398
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the word "Coll"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or concept related to "Collage."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tub
    -0.73
    urai
    -0.71
    pipe
    -0.69
     quota
    -0.68
    abyte
    -0.66
     tad
    -0.66
    RAM
    -0.66
     devote
    -0.64
    abytes
    -0.64
     tradition
    -0.63
    POSITIVE LOGITS
     Coll
    3.78
    Coll
    2.98
    coll
    2.91
     coll
    2.02
     Collider
    1.32
     Crash
    1.30
     collision
    1.30
     collar
    1.18
     collisions
    1.15
     collide
    1.15
    Activations Density 0.029%

    No Known Activations