© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 16454
    Prev
    Next
    INDEX
    Explanations

    stems of the word "hope" and related words indicating optimism

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hope and positive expectations about outcomes

    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
     Originally
    -0.65
    arently
    -0.62
    irm
    -0.61
    ãĤ»
    -0.61
     Apparently
    -0.58
    romy
    -0.57
    zai
    -0.55
    nil
    -0.55
     obligatory
    -0.55
    arget
    -0.54
    POSITIVE LOGITS
     will
    1.46
    will
    1.40
    'll
    1.15
    Will
    1.12
     someday
    1.09
     WILL
    1.07
    won
    1.00
     won
    0.98
     would
    0.96
    would
    0.93
    Activations Density 0.397%

    No Known Activations