© 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
    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. 7901
    Prev
    Next
    INDEX
    Explanations

    fruits and grains

    oai_token-act-pair · gpt-3.5-turbo

    words related to tangible objects or concepts that convey a sense of substance or value

    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
     Princ
    -0.49
     [+
    -0.48
     âĢİ
    -0.47
     ·
    -0.46
     discourse
    -0.44
     Languages
    -0.44
     vulgar
    -0.44
     WOM
    -0.44
     languages
    -0.43
     hating
    -0.43
    POSITIVE LOGITS
    luster
    0.74
    iple
    0.71
    imum
    0.67
    itures
    0.64
    ifully
    0.63
    eto
    0.63
    iful
    0.62
    ily
    0.61
    itial
    0.61
    ively
    0.61
    Activations Density 0.445%

    No Known Activations