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. 22016
    Prev
    Next
    INDEX
    Explanations

    proper names or entities, particularly ones starting with the letter "J"

    oai_token-act-pair · gpt-3.5-turbo

    instances of Pokémon character descriptions

    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
     galleries
    -0.68
     MacArthur
    -0.64
     Cind
    -0.64
     pony
    -0.64
     captcha
    -0.63
    houses
    -0.61
     beware
    -0.61
     Crest
    -0.61
    ciation
    -0.60
    doors
    -0.59
    POSITIVE LOGITS
    upiter
    1.40
    unction
    1.32
    ourney
    1.32
    ournals
    1.30
    ealous
    1.25
    avascript
    1.25
    umping
    1.24
    igsaw
    1.24
    oint
    1.23
    acket
    1.23
    Activations Density 0.037%

    No Known Activations