Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 9206
    Prev
    Next
    INDEX
    Explanations

    specific mentions of software tools or products within a document

    oai_token-act-pair · gpt-3.5-turbo

    references to the creation and regulation of digital content or software

    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
     again
    -0.70
    ivas
    -0.69
     nonetheless
    -0.66
     acknow
    -0.66
    disabled
    -0.65
    nown
    -0.64
     indeed
    -0.64
     poised
    -0.63
    iful
    -0.62
     estab
    -0.62
    POSITIVE LOGITS
     Ago
    0.66
     SCP
    0.65
    ammers
    0.64
     previous
    0.61
     CPC
    0.59
    isse
    0.59
     Step
    0.53
     this
    0.53
     Lug
    0.52
    ahu
    0.52
    Activations Density 0.489%

    No Known Activations