© 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. 2-RES-JB
    11. 20931
    Prev
    Next
    INDEX
    Explanations

    words related to things floating or being elevated above ground

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "flow."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nan
    -0.80
    Interstitial
    -0.78
     equity
    -0.76
    */(
    -0.74
    âĶģ
    -0.72
     Authorities
    -0.69
    Ô
    -0.68
     Equity
    -0.67
     Annotations
    -0.67
    ettings
    -0.66
    POSITIVE LOGITS
     flo
    1.36
    flo
    0.96
    pped
    0.96
    ftime
    0.91
    pping
    0.87
    arding
    0.86
    ppings
    0.84
    wu
    0.83
    orescence
    0.80
    arded
    0.79
    Activations Density 0.008%

    No Known Activations