© 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. 9-RES-JB
    11. 1019
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a series of examples or a list

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the existence or presence of stories and facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    culosis
    -0.78
    nesday
    -0.78
    oire
    -0.78
    iliation
    -0.72
    etheless
    -0.72
    aea
    -0.71
    oyer
    -0.70
    ility
    -0.70
    icka
    -0.69
    ãĤ¨ãĥ«
    -0.69
    POSITIVE LOGITS
    types
    0.91
     examples
    0.89
     truths
    0.87
     constants
    0.82
     facts
    0.81
     guys
    0.80
     kinds
    0.79
     caveats
    0.78
     types
    0.77
     topics
    0.76
    Activations Density 0.064%

    No Known Activations