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. 2-RES-JB
    6. 22624
    Prev
    Next
    INDEX
    Explanations

    words related to the use or application of something, particularly in the context of technology or development

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of utility or practical application

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    beard
    -0.75
     Empires
    -0.73
    oslov
    -0.71
     ethical
    -0.68
     Hust
    -0.66
     Nose
    -0.65
     gulf
    -0.64
     publishers
    -0.63
    hair
    -0.63
    cot
    -0.62
    POSITIVE LOGITS
    izations
    1.19
    izable
    1.18
    ization
    1.14
    isation
    1.12
    ised
    1.10
    ocated
    1.09
    util
    1.09
    ized
    1.07
    ãĥ¼ãĥĨãĤ£
    1.06
    itation
    1.05
    Activations Density 0.003%

    No Known Activations