© 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. 11775
    Prev
    Next
    INDEX
    Explanations

    denials or refutations in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of denial or disavowal regarding accusations or claims made against individuals or groups

    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
    ngth
    -0.89
    soDeliveryDate
    -0.78
     Scores
    -0.75
    loo
    -0.72
    Ec
    -0.68
     brackets
    -0.67
    mac
    -0.67
    TW
    -0.66
    wal
    -0.66
    alid
    -0.66
    POSITIVE LOGITS
     existence
    0.96
     outright
    0.95
     exist
    0.93
     legitimacy
    0.92
     paternity
    0.90
     validity
    0.89
     slightest
    0.87
     consent
    0.83
     authenticity
    0.82
     spurious
    0.80
    Activations Density 0.085%

    No Known Activations