© 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. 23440
    Prev
    Next
    INDEX
    Explanations

    exciting or enthusiastic terms

    oai_token-act-pair · gpt-3.5-turbo

    expressions of excitement and enthusiasm

    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
     greens
    -0.81
    DragonMagazine
    -0.73
    loo
    -0.63
    folk
    -0.63
     quarters
    -0.61
     hash
    -0.61
    hip
    -0.61
    mint
    -0.60
    part
    -0.60
     lightsaber
    -0.60
    POSITIVE LOGITS
    itement
    1.20
    Exc
    1.06
    exc
    1.05
     Exc
    0.94
    ursor
    0.90
    ruciating
    0.90
    ursion
    0.89
    uses
    0.86
    asper
    0.84
    ptive
    0.84
    Activations Density 0.010%

    No Known Activations