© 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. 11-RES-JB
    11. 10020
    Prev
    Next
    INDEX
    Explanations

    phrases indicating excitement and accomplishment

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "we" and its variants, indicating collective sentiment or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itates
    -0.65
    Appearances
    -0.64
     Flavoring
    -0.62
    itary
    -0.57
     offending
    -0.57
    rift
    -0.57
    uces
    -0.56
    Pref
    -0.56
    entary
    -0.55
    dust
    -0.55
    POSITIVE LOGITS
    're
    1.34
    've
    1.27
     intend
    1.08
     anticipate
    1.07
     are
    1.00
     strive
    0.98
    akening
    0.92
     believe
    0.92
     hope
    0.90
    'll
    0.90
    Activations Density 0.198%

    No Known Activations