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. 9-RES-JB
    6. 6608
    Prev
    Next
    INDEX
    Explanations

    mentions of impactful changes and developments in various environments

    oai_token-act-pair · gpt-3.5-turbo

    expressions of social and political impacts related to health and community well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ['
    -0.73
    £ı
    -0.73
     [+
    -0.68
     Âł Âł Âł Âł Âł Âł Âł Âł
    -0.66
     ((
    -0.66
     Simulator
    -0.65
    aughs
    -0.63
     ["
    -0.62
     ³³
    -0.61
    hari
    -0.61
    POSITIVE LOGITS
     nonetheless
    0.86
     downright
    0.83
     overlooked
    0.73
     homegrown
    0.72
    etheless
    0.67
     intangible
    0.64
     lawmakers
    0.60
     payday
    0.60
     nevertheless
    0.59
     bystanders
    0.59
    Activations Density 1.280%

    No Known Activations