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. 5863
    Prev
    Next
    INDEX
    Explanations

    direct quotations in text

    oai_token-act-pair · gpt-3.5-turbo

    statements that reference quotes and attributions

    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
    kt
    -0.64
    brance
    -0.63
    cycle
    -0.62
    ãĥĺ
    -0.60
    hemer
    -0.59
    light
    -0.59
    Visit
    -0.59
    Join
    -0.59
    BOX
    -0.59
     Medals
    -0.58
    POSITIVE LOGITS
     saying
    0.91
     Saying
    0.80
     citing
    0.79
    terday
    0.78
     describing
    0.76
     explaining
    0.75
    ulin
    0.74
     cited
    0.74
     sounding
    0.70
     stating
    0.70
    Activations Density 0.087%

    No Known Activations