© 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. 3-RES-JB
    11. 1790
    Prev
    Next
    INDEX
    Explanations

    phrases related to unsupported or unproven claims

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that indicate claims or concerns that are lacking in evidence or validity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebus
    -0.96
    azine
    -0.84
    itte
    -0.81
    ophon
    -0.79
    hedral
    -0.76
    odan
    -0.75
    emis
    -0.72
    lite
    -0.71
    reon
    -0.70
    igslist
    -0.69
    POSITIVE LOGITS
     unfounded
    0.88
     optimism
    0.85
    nesses
    0.81
     belief
    0.81
     indignation
    0.79
     suspicions
    0.79
     speculation
    0.77
     accusations
    0.77
     curiosity
    0.77
     outrage
    0.77
    Activations Density 0.018%

    No Known Activations