Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 15241
    Prev
    Next
    INDEX
    Explanations

    references to political figures

    oai_token-act-pair · gpt-3.5-turbo

    names and notable individuals or references in current events

    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
    ruction
    -0.66
    "],
    -0.65
    "]=>
    -0.62
    ombat
    -0.61
     departures
    -0.61
    *:
    -0.59
    ":"/
    -0.59
    odes
    -0.58
    gram
    -0.58
    jer
    -0.57
    POSITIVE LOGITS
     aka
    0.96
     albeit
    0.86
     along
    0.83
     formerly
    0.78
     fearing
    0.78
     accompanied
    0.76
     hitherto
    0.76
     aided
    0.74
     flanked
    0.74
     alongside
    0.72
    Activations Density 0.239%

    No Known Activations