© 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. 0-RES-JB
    11. 1183
    Prev
    Next
    INDEX
    Explanations

    various scenarios where people express hope or anticipation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hoped."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Detail
    -0.63
    erent
    -0.60
     override
    -0.59
    roc
    -0.58
     01
    -0.56
     Citation
    -0.56
     Elements
    -0.56
    Da
    -0.55
     Examples
    -0.55
    01
    -0.54
    POSITIVE LOGITS
     hoped
    3.58
     hopes
    1.93
     hope
    1.79
     anticipated
    1.64
     feared
    1.64
     wished
    1.57
     hoping
    1.49
     expected
    1.49
     envisioned
    1.48
     planned
    1.47
    Activations Density 0.008%

    No Known Activations