© 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. 7-RES-JB
    11. 13519
    Prev
    Next
    INDEX
    Explanations

    phrases related to fear and being scared

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing fear or anxiety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 7 - fear

    No Comments

    Negative Logits
    issance
    -0.94
    loe
    -0.77
    swick
    -0.76
    eret
    -0.75
    ellery
    -0.73
    MX
    -0.73
    estone
    -0.73
    aepernick
    -0.73
     converter
    -0.72
    rett
    -0.72
    POSITIVE LOGITS
     repr
    1.18
     retribution
    1.08
     heights
    1.08
     retaliation
    0.99
     reperc
    0.84
     persecution
    0.84
     ghosts
    0.83
     repercussions
    0.83
     wrath
    0.82
     intimidation
    0.80
    Activations Density 0.090%

    No Known Activations