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. 10743
    Prev
    Next
    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'i' and its various forms, indicating a strong focus on first-person perspective and subjective experience

    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
     Parables
    -0.68
    jri
    -0.68
    =-=-=-=-
    -0.66
    retty
    -0.66
     needle
    -0.65
     straw
    -0.65
     diarr
    -0.63
     maize
    -0.63
     lashes
    -0.62
     tuber
    -0.61
    POSITIVE LOGITS
    Tech
    0.92
    Corp
    0.84
    Fi
    0.83
    plex
    0.81
    engine
    0.81
    cession
    0.80
    jet
    0.79
    STAR
    0.79
    formed
    0.76
    galitarian
    0.74
    Activations Density 0.096%

    No Known Activations