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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 10677
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "in the first place."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "first" in various contexts

    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
    apego
    -0.74
    uties
    -0.70
     staples
    -0.66
    othing
    -0.65
    paio
    -0.65
    ourge
    -0.63
     faults
    -0.61
    rish
    -0.60
    ocide
    -0.60
     brakes
    -0.60
    POSITIVE LOGITS
     nutshell
    0.99
     vicinity
    0.98
     guise
    0.92
     vein
    0.87
     midst
    0.84
     manner
    0.83
     context
    0.82
     courtyard
    0.80
     hurry
    0.78
    ixties
    0.77
    Activations Density 0.145%

    No Known Activations