© 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. 8-RES-JB
    11. 18450
    Prev
    Next
    INDEX
    Explanations

    names or terms related to specific individuals or entities, particularly those with the letters "Re" and "eb"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific names or terms related to individuals, likely in a context of controversy or legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    »Ĵ
    -0.74
    ashtra
    -0.69
     wa
    -0.65
    ulhu
    -0.63
    æĪ¦
    -0.60
    acca
    -0.59
     liner
    -0.58
     respectively
    -0.57
     intrins
    -0.56
     Nadu
    -0.56
    POSITIVE LOGITS
    itory
    0.86
    ndum
    0.83
    issance
    0.82
    earch
    0.82
     Priebus
    0.80
    inion
    0.77
    burse
    0.76
     Tayyip
    0.72
    irmation
    0.72
    otiation
    0.71
    Activations Density 0.087%

    No Known Activations