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. 6-RES-JB
    6. 13196
    Prev
    Next
    INDEX
    Explanations

    dates mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIDEOS
    -0.80
    éļ
    -0.78
    plet
    -0.73
    akia
    -0.73
    ãģĤ
    -0.71
    bourg
    -0.70
    olate
    -0.70
    ãģķ
    -0.70
    å§«
    -0.69
    ierrez
    -0.69
    POSITIVE LOGITS
    lights
    0.72
    lies
    0.71
    nings
    0.65
     clerk
    0.62
    liest
    0.61
     Judith
    0.61
     Theresa
    0.61
     she
    0.59
     Went
    0.59
     closest
    0.58
    Activations Density 0.079%

    No Known Activations