© 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. 7482
    Prev
    Next
    INDEX
    Explanations

    references to factual information in a text

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to "facts" in various contexts

    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
    yss
    -0.92
    ovo
    -0.84
    osi
    -0.82
    isoft
    -0.80
    antha
    -0.79
    zik
    -0.78
    rint
    -0.77
    ateurs
    -0.76
    irl
    -0.76
    hod
    -0.76
    POSITIVE LOGITS
    facts
    0.94
     facts
    0.93
    heet
    0.87
    fulness
    0.83
     inacc
    0.82
    fact
    0.82
    telling
    0.78
     unfold
    0.72
     pertaining
    0.71
     relating
    0.69
    Activations Density 0.022%

    No Known Activations