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. 10663
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "each" or "every" is used to reference individual entities within a group

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "each" and other terms indicating a count or inclusion of individual items

    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
    tis
    -0.77
    casters
    -0.73
    ourge
    -0.72
    uties
    -0.68
    ulner
    -0.68
    iversary
    -0.66
    stars
    -0.66
    ographers
    -0.66
    rists
    -0.65
    ocide
    -0.65
    POSITIVE LOGITS
     vicinity
    1.22
     manner
    1.21
     guise
    1.18
     context
    1.08
     vein
    1.06
     midst
    1.03
     direction
    0.99
     respects
    0.96
     contexts
    0.95
     regard
    0.91
    Activations Density 0.202%

    No Known Activations