© 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. 11-RES-JB
    11. 22495
    Prev
    Next
    INDEX
    Explanations

    phrases related to naming or identifying specific things or individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe the current state or identification of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gap
    -0.66
    azar
    -0.61
    conn
    -0.60
    ertodd
    -0.58
    atana
    -0.56
    acio
    -0.54
     gaps
    -0.54
    ason
    -0.53
     NAACP
    -0.53
     Monitoring
    -0.53
    POSITIVE LOGITS
     wont
    1.16
     nowadays
    0.90
     today
    0.87
    now
    0.79
    lished
    0.77
     presently
    0.75
    today
    0.73
    named
    0.71
     portrayed
    0.71
     anyways
    0.71
    Activations Density 0.141%

    No Known Activations