© 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. 12123
    Prev
    Next
    INDEX
    Explanations

    phrases related to unity and support within a community

    oai_token-act-pair · gpt-3.5-turbo
    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
    itarian
    -0.71
    iple
    -0.65
    uman
    -0.62
    assian
    -0.60
    è£ħ
    -0.60
    perture
    -0.59
     (âĪĴ
    -0.58
    eton
    -0.58
    Proxy
    -0.57
    emonium
    -0.56
    POSITIVE LOGITS
     regardless
    1.06
     namely
    1.04
     irrespective
    0.96
     especially
    0.93
     wherever
    0.88
     including
    0.88
    especially
    0.87
    whether
    0.86
     whether
    0.85
    particularly
    0.85
    Activations Density 0.241%

    No Known Activations