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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 3623
    Prev
    Next
    INDEX
    Explanations

    functional relationships and consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causation or consequences

    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
     Ernst
    -0.66
    anka
    -0.65
    uary
    -0.62
     Myster
    -0.59
    ohm
    -0.59
    ato
    -0.59
     struck
    -0.58
    iana
    -0.58
     Watt
    -0.58
    iol
    -0.58
    POSITIVE LOGITS
     exponentially
    0.70
    hift
    0.70
     enormously
    0.67
     lots
    0.66
     immersion
    0.65
    otes
    0.64
     elevation
    0.64
     unwanted
    0.64
    incre
    0.64
     undue
    0.63
    Activations Density 0.319%

    No Known Activations