© 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. 12046
    Prev
    Next
    INDEX
    Explanations

    instances of negative statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "not"

    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
    CRIP
    -0.67
    æĥ
    -0.67
    ++++
    -0.65
    éĥ
    -0.64
    GEN
    -0.61
    Pierre
    -0.60
    rift
    -0.60
    vice
    -0.60
    Pr
    -0.60
     Spectrum
    -0.59
    POSITIVE LOGITS
     yet
    1.09
     been
    1.08
    epad
    1.03
    icably
    1.01
    icable
    0.99
    yet
    0.96
     necessarily
    0.93
    hin
    0.93
     gotten
    0.91
    been
    0.89
    Activations Density 0.051%

    No Known Activations