© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 21800
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the publication or issue of a magazine or journal

    oai_token-act-pair · gpt-3.5-turbo

    references to magazine issues and their contents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rophic
    -0.74
    bones
    -0.70
    urally
    -0.66
    heed
    -0.65
     disparate
    -0.63
    eric
    -0.62
     backbone
    -0.61
    rous
    -0.61
    roo
    -0.61
    raltar
    -0.59
    POSITIVE LOGITS
    Magazine
    0.79
     Comics
    0.76
    rint
    0.74
    Journal
    0.73
     thereof
    0.72
    ials
    0.72
    arium
    0.72
    Newsletter
    0.72
    Reader
    0.71
    agents
    0.71
    Activations Density 0.040%

    No Known Activations