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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1839
    Prev
    Next
    INDEX
    Explanations

    references to "Hasbro" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the brand "Hasbro."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gins
    -0.68
    orious
    -0.66
    Prim
    -0.64
     Noon
    -0.61
     Dull
    -0.60
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.60
     Nir
    -0.59
     famed
    -0.58
    aries
    -0.58
     outfield
    -0.58
    POSITIVE LOGITS
    ccoli
    1.20
    bro
    1.11
    idered
    1.00
    keye
    0.94
    afort
    0.92
    vity
    0.91
    kes
    0.91
    cffff
    0.90
    kef
    0.90
    oke
    0.90
    Activations Density 0.010%

    No Known Activations