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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-RES-JB
    6. 9317
    Prev
    Next
    INDEX
    Explanations

    events or incidents that have occurred or are happening

    oai_token-act-pair · gpt-3.5-turbo

    present tense verbs indicating actions or events

    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
     marg
    -0.66
     domest
    -0.63
     fishes
    -0.63
     conqu
    -0.62
     Monstrous
    -0.62
    iate
    -0.61
     Cyr
    -0.60
    ËĪ
    -0.59
     facult
    -0.58
     zones
    -0.57
    POSITIVE LOGITS
    ¿½
    0.84
    ackets
    0.79
    ozy
    0.79
    itled
    0.78
     showc
    0.77
    lehem
    0.76
    INO
    0.75
    ASHINGTON
    0.73
    undown
    0.71
    oother
    0.71
    Activations Density 0.399%

    No Known Activations