© 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. 8-RES-JB
    11. 10562
    Prev
    Next
    INDEX
    Explanations

    phrases pointing out specific statements or quotes within a longer text

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the symbol 'Ļ'

    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
    igraph
    -0.88
    chnology
    -0.80
    anmar
    -0.78
    ctors
    -0.75
    inent
    -0.73
    agra
    -0.73
    osion
    -0.70
    undown
    -0.70
    agna
    -0.70
    FactoryReloaded
    -0.68
    POSITIVE LOGITS
     namely
    0.95
     whereas
    0.88
     Including
    0.82
    said
    0.81
    SOURCE
    0.72
     Ibid
    0.71
     although
    0.68
     yea
    0.68
    which
    0.66
    according
    0.65
    Activations Density 0.141%

    No Known Activations