© 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. 2874
    Prev
    Next
    INDEX
    Explanations

    words related to feelings of concern or anxiety

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating concern or anxiety

    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
     completion
    -0.73
    form
    -0.63
    aug
    -0.61
    complete
    -0.61
     Redemption
    -0.60
     excellence
    -0.60
    ultimate
    -0.60
    ext
    -0.59
     acquisition
    -0.59
     initiation
    -0.59
    POSITIVE LOGITS
     worried
    3.35
     concerned
    2.27
     worries
    1.93
     worry
    1.92
     alarmed
    1.87
     scared
    1.81
     terrified
    1.76
     panicked
    1.76
     worrying
    1.73
     frightened
    1.71
    Activations Density 0.013%

    No Known Activations