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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 6423
    Prev
    Next
    INDEX
    Explanations

    explicit statements or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of opinion or subjective statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     allegedly
    -0.69
    rawdownloadcloneembedreportprint
    -0.69
    uga
    -0.64
    mouse
    -0.63
    ÄŁ
    -0.62
     sche
    -0.62
    aspx
    -0.62
     grid
    -0.61
     fil
    -0.60
    uses
    -0.59
    POSITIVE LOGITS
    xus
    0.84
    é¾į
    0.72
    ictionary
    0.67
    uce
    0.66
    âĶĢâĶĢâĶĢâĶĢ
    0.65
     TAMADRA
    0.65
    geist
    0.65
    Edward
    0.64
    arden
    0.63
     icing
    0.62
    Activations Density 0.053%

    No Known Activations