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. 0-RES-JB
    6. 14243
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'cynabal'

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific brand or product related to technology

    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
     Tennessee
    -0.73
     NS
    -0.69
     Jennings
    -0.68
     Sony
    -0.66
     Shot
    -0.65
     plaintiff
    -0.61
     Pres
    -0.61
     America
    -0.60
     Schmidt
    -0.59
     reinstated
    -0.58
    POSITIVE LOGITS
    abal
    5.30
     cabal
    1.27
    kell
    1.08
    ambo
    1.05
    ibal
    1.03
    ulhu
    0.99
    alid
    0.99
     Haskell
    0.99
    ursed
    0.98
    alam
    0.94
    Activations Density 0.032%

    No Known Activations