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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 22574
    Prev
    Next
    INDEX
    Explanations

    words related to additional or supplementary concepts

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to alternative medicine or therapies

    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
    manship
    -0.89
    olicy
    -0.84
    gerald
    -0.80
     Generations
    -0.77
    ly
    -0.76
    leness
    -0.74
    odan
    -0.74
    lio
    -0.74
    lies
    -0.72
    hov
    -0.72
    POSITIVE LOGITS
    ization
    1.32
    ized
    1.22
    izing
    1.19
    ised
    1.15
    ize
    1.13
    isation
    1.09
    istic
    1.08
    ogical
    1.07
    ists
    1.03
    izable
    1.03
    Activations Density 0.089%

    No Known Activations