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. 0-RES-JB
    6. 7244
    Prev
    Next
    INDEX
    Explanations

    advertisements within the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of advertisements and specific people's names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CVE
    -0.77
    colour
    -0.73
    oké
    -0.69
     Sparrow
    -0.67
    AME
    -0.65
    ggle
    -0.64
    ould
    -0.63
     east
    -0.63
    atham
    -0.62
    nces
    -0.61
    POSITIVE LOGITS
     Advertisement
    2.06
    uren
    1.68
    ensen
    1.51
     slideshow
    1.24
    SPONSORED
    1.20
    Continue
    1.19
     Mahmoud
    1.17
    Via
    1.15
    zynski
    1.10
     Friedman
    0.99
    Activations Density 0.050%

    No Known Activations