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. 3-RES-JB
    6. 7984
    Prev
    Next
    INDEX
    Explanations

    mentions of institutions or organizations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific organizations or committees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jured
    -0.67
     combustion
    -0.67
    animate
    -0.66
    atsuki
    -0.65
     trouble
    -0.64
     symptoms
    -0.64
     idle
    -0.64
    assed
    -0.63
     kernels
    -0.63
     beasts
    -0.63
    POSITIVE LOGITS
     respectively
    1.02
     headquartered
    0.95
     etc
    0.91
     aka
    0.88
     chaired
    0.87
    76561
    0.81
     meanwhile
    0.80
     which
    0.79
    SPONSORED
    0.79
     including
    0.78
    Activations Density 1.035%

    No Known Activations