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. 9338
    Prev
    Next
    INDEX
    Explanations

    specific details or conditions that are emphasized or singled out

    oai_token-act-pair · gpt-3.5-turbo

    references to "certain" criteria or conditions

    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
    DragonMagazine
    -0.81
    inson
    -0.73
    TeX
    -0.72
    perse
    -0.71
    ITAL
    -0.70
     Cum
    -0.69
     thence
    -0.69
    annis
    -0.68
    INT
    -0.68
    JV
    -0.68
    POSITIVE LOGITS
    ties
    1.45
     kinds
    1.19
     types
    1.00
     wavelengths
    0.93
    iated
    0.90
     aspects
    0.89
    iating
    0.89
     circumstances
    0.83
     parts
    0.82
     regions
    0.82
    Activations Density 0.022%

    No Known Activations