© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 1915
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific historical figures or locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of prominent figures and places

    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
    ruary
    -0.83
    ĨĴ
    -0.72
    irlf
    -0.72
     Nicarag
    -0.65
    aler
    -0.64
    glers
    -0.63
    Dispatch
    -0.63
     SERV
    -0.59
    bilt
    -0.59
    ãĤ£
    -0.58
    POSITIVE LOGITS
    yna
    0.80
    ı
    0.80
    hani
    0.80
    nis
    0.78
    vu
    0.77
    schild
    0.76
    hai
    0.76
     è£ıè
    0.75
    ahi
    0.72
    oola
    0.71
    Activations Density 0.257%

    No Known Activations