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. 5806
    Prev
    Next
    INDEX
    Explanations

    financial values and estimations

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and estimates related to various subjects

    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
    inge
    -0.73
    ework
    -0.72
    papers
    -0.69
    anza
    -0.67
    ighting
    -0.65
    emetery
    -0.65
    ador
    -0.64
    iatus
    -0.63
    ifles
    -0.63
    erto
    -0.62
    POSITIVE LOGITS
     approx
    0.96
     ¥
    0.91
     105
    0.87
     175
    0.83
     $
    0.83
     350
    0.83
     580
    0.83
     380
    0.81
     550
    0.81
     190
    0.80
    Activations Density 0.246%

    No Known Activations