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. 22238
    Prev
    Next
    INDEX
    Explanations

    phrases related to breaking something into parts or analyzing information in detail

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of breaking down or analyzing situations or objects

    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
    mong
    -0.75
    inen
    -0.74
    arak
    -0.72
    jab
    -0.71
     endors
    -0.66
     Jinn
    -0.65
     awa
    -0.64
    ught
    -0.64
    Mp
    -0.63
     retracted
    -0.62
    POSITIVE LOGITS
    sheets
    0.94
    stairs
    0.92
    river
    0.91
    taining
    0.72
    inately
    0.71
    sheet
    0.71
    grading
    0.69
    cled
    0.69
     sheets
    0.67
     barriers
    0.67
    Activations Density 0.013%

    No Known Activations