© 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. 17258
    Prev
    Next
    INDEX
    Explanations

    words related to specific cultural or technical terms, such as musical instruments or scientific concepts

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to traditional music, plants, and dialects

    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
     Accountability
    -0.99
     Aging
    -0.87
     Applicant
    -0.82
    Money
    -0.80
    Imm
    -0.77
    Spons
    -0.76
    ©¶æ¥µ
    -0.76
     Task
    -0.76
    Writ
    -0.76
    ADRA
    -0.76
    POSITIVE LOGITS
    xual
    1.14
    hed
    0.89
    onal
    0.85
    igans
    0.84
    tarian
    0.84
    ciation
    0.82
    ldom
    0.82
    hers
    0.80
    cies
    0.79
    lic
    0.78
    Activations Density 0.448%

    No Known Activations