© 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. 7-RES-JB
    11. 3098
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement or progression

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cius
    -0.72
    ilings
    -0.68
    grave
    -0.68
    arus
    -0.66
     Corpus
    -0.63
     livest
    -0.62
    ilts
    -0.62
    urses
    -0.61
     Kau
    -0.61
    atus
    -0.60
    POSITIVE LOGITS
    ward
    0.96
    DragonMagazine
    0.91
     toward
    0.89
    fare
    0.88
     towards
    0.87
    finder
    0.85
     into
    0.83
     onto
    0.82
     INTO
    0.81
    é¾įåĸļ士
    0.79
    Activations Density 0.023%

    No Known Activations