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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 3414
    Prev
    Next
    INDEX
    Explanations

    instances where something is interpreted as a significant or meaningful signal

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating signs or signals of various situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quer
    -0.76
    ancies
    -0.73
     livest
    -0.71
     swaps
    -0.67
    ecycle
    -0.65
     sacrific
    -0.65
    elta
    -0.65
    asus
    -0.63
     freezes
    -0.63
    ascus
    -0.62
    POSITIVE LOGITS
     of
    0.85
    posts
    0.82
     thereof
    0.77
    ifier
    0.73
     that
    0.73
     indicative
    0.73
    atory
    0.73
     indicating
    0.73
    post
    0.73
    ariat
    0.70
    Activations Density 0.079%

    No Known Activations