© 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. 6-RES-JB
    11. 17170
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "But there are" or similar structures indicating contrasting information

    oai_token-act-pair · gpt-3.5-turbo

    discussions about restrictions and challenges in various contexts

    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
    but
    -0.69
    Tonight
    -0.66
     but
    -0.64
     However
    -0.64
    However
    -0.63
    kat
    -0.62
     tv
    -0.61
     fixme
    -0.61
     [|
    -0.60
    alde
    -0.60
    POSITIVE LOGITS
     nonetheless
    1.08
    etheless
    1.03
     nevertheless
    0.86
     persisted
    0.77
     overshadowed
    0.76
     persists
    0.75
     undeniably
    0.75
     dogged
    0.74
     balk
    0.73
     elusive
    0.73
    Activations Density 1.015%

    No Known Activations