© 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. 9-RES-JB
    11. 4969
    Prev
    Next
    INDEX
    Explanations

    phrases related to numerical quantities or large groups of people

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating frequency or quantity, especially in political contexts

    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
    )</
    -0.70
    runtime
    -0.70
     haha
    -0.68
     Alone
    -0.63
     ;)
    -0.62
     ðŁĻĤ
    -0.62
    Anything
    -0.62
    ','
    -0.62
    gt
    -0.62
    anything
    -0.61
    POSITIVE LOGITS
     commentators
    1.22
     commenters
    1.16
     observers
    1.13
     analysts
    1.08
     scholars
    1.06
     prominent
    1.03
     experts
    0.95
     indications
    0.95
     lawmakers
    0.94
     organizations
    0.94
    Activations Density 0.234%

    No Known Activations