© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 21795
    Prev
    Next
    INDEX
    Explanations

    terms related to forum structure and discussion moderation

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to online community interactions and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forth
    -0.75
     cautiously
    -0.69
     manif
    -0.67
     primed
    -0.65
     imagining
    -0.65
    ÅŁ
    -0.64
     interrogation
    -0.64
     contingency
    -0.64
     ramp
    -0.63
     leaping
    -0.63
    POSITIVE LOGITS
     Reviews
    1.20
     Description
    1.13
    ategories
    1.07
     Submit
    1.06
     Featured
    1.06
     Favorite
    1.06
     Ratings
    1.03
     Browse
    1.02
     Categories
    1.02
     Posts
    1.00
    Activations Density 0.622%

    No Known Activations