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. 8148
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions or events happening

    oai_token-act-pair · gpt-3.5-turbo

    isolated clauses that provide context or details in a sentence

    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
    ety
    -0.70
    ¬¼
    -0.70
    raved
    -0.69
    iple
    -0.64
    rite
    -0.63
    rio
    -0.63
    ITE
    -0.61
    ocl
    -0.61
    scription
    -0.59
     Founding
    -0.59
    POSITIVE LOGITS
     whereas
    1.13
     thereby
    1.09
     respectively
    1.06
     regardless
    1.03
     preferably
    0.97
     resulting
    0.95
     namely
    0.94
     etc
    0.94
     although
    0.92
     depending
    0.92
    Activations Density 0.810%

    No Known Activations