© 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. 8-RES-JB
    11. 20156
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or actions that trigger a response or a change

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "the."

    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
    lly
    -0.82
    ãĥĦ
    -0.76
    ãĤ´ãĥ³
    -0.74
    <?
    -0.73
    âĺ
    -0.72
    ca
    -0.72
     è£ıè
    -0.71
    dan
    -0.71
    mobi
    -0.70
    bourg
    -0.69
    POSITIVE LOGITS
     slightest
    1.09
     latter
    1.00
     curtain
    0.96
     tide
    0.94
     dust
    0.92
     doors
    0.91
     rains
    0.91
     opportunity
    0.89
     interviewer
    0.87
     lid
    0.87
    Activations Density 0.175%

    No Known Activations