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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 5388
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or decisions made by a group of people

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people or entities in a plural form

    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
     open
    -0.67
     arm
    -0.66
     golf
    -0.65
     ice
    -0.64
     high
    -0.62
     convention
    -0.62
     level
    -0.62
     cap
    -0.61
     tail
    -0.61
     bow
    -0.60
    POSITIVE LOGITS
    they
    3.25
    their
    2.24
    them
    1.98
    these
    1.82
    there
    1.76
    you
    1.66
    those
    1.65
    she
    1.49
    we
    1.45
    They
    1.45
    Activations Density 0.007%

    No Known Activations