© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11049
    Prev
    Next
    INDEX
    Explanations

    religious and political gatherings or addresses

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of addresses or speeches given to groups

    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
    Prev
    -0.66
    agate
    -0.64
    angler
    -0.64
     inhibitor
    -0.63
    _-
    -0.60
    zu
    -0.60
    nan
    -0.60
     maps
    -0.59
    âĨij
    -0.59
    styles
    -0.58
    POSITIVE LOGITS
     audience
    1.36
     assembled
    1.36
     audiences
    1.32
     crowds
    1.32
     crowd
    1.27
     gathered
    1.22
     listeners
    1.22
     applause
    1.20
     attendees
    1.19
     delegates
    1.15
    Activations Density 0.243%

    No Known Activations