© 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. 4-RES-JB
    11. 22097
    Prev
    Next
    INDEX
    Explanations

    instances of false information and declarations

    oai_token-act-pair · gpt-3.5-turbo

    references to falsehoods and deception

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

    No Comments

    Negative Logits
     largeDownload
    -0.77
    zens
    -0.74
    rared
    -0.71
    mopolitan
    -0.71
    leground
    -0.69
    oval
    -0.68
    anian
    -0.68
    ificent
    -0.68
    idential
    -0.67
    igree
    -0.67
    POSITIVE LOGITS
    ãĤ¹ãĥĪ
    0.78
     attribut
    0.76
     omission
    0.75
     Prometheus
    0.74
     miscar
    0.72
     mistaken
    0.71
     assumptions
    0.70
    Ö¼
    0.68
     excuse
    0.65
     Loki
    0.64
    Activations Density 0.412%

    No Known Activations