© 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. 10-RES-JB
    11. 20305
    Prev
    Next
    INDEX
    Explanations

    instances of fear or anxiety associated with various scenarios or conditions

    oai_token-act-pair · gpt-3.5-turbo

    various expressions of fear and anxiety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 10 - fear

    No Comments

    Negative Logits
    DragonMagazine
    -0.89
    issance
    -0.84
    Sport
    -0.75
    idelines
    -0.74
    ession
    -0.73
    Sort
    -0.71
    arta
    -0.70
    ï¸ı
    -0.67
    Enabled
    -0.67
    unny
    -0.67
    POSITIVE LOGITS
     heights
    1.28
     repr
    1.25
     losing
    1.22
     retribution
    1.14
     repercussions
    1.12
     reperc
    1.11
     encountering
    1.10
     retaliation
    1.08
     offending
    1.04
     upsetting
    1.00
    Activations Density 0.093%

    No Known Activations