© 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. 24018
    Prev
    Next
    INDEX
    Explanations

    terms related to communities and systems within them

    oai_token-act-pair · gpt-3.5-turbo

    references to community and societal dynamics

    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
     Assist
    -0.62
    borgh
    -0.62
    cott
    -0.61
    nesday
    -0.61
     expired
    -0.60
    è£ħ
    -0.59
    ãĥīãĥ©
    -0.58
    Exception
    -0.58
    ursday
    -0.58
     Partial
    -0.58
    POSITIVE LOGITS
     itself
    1.22
    osphere
    1.02
     they
    0.98
     surrounding
    0.96
     THEY
    0.96
     quo
    0.94
     unfolding
    0.90
     entrusted
    0.89
    geist
    0.86
     we
    0.84
    Activations Density 0.349%

    No Known Activations