© 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. 10-RES-JB
    6. 24358
    Prev
    Next
    INDEX
    Explanations

    mentions of fear or being afraid

    oai_token-act-pair · gpt-3.5-turbo

    expressions of fear or anxiety about safety or risk

    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
    nice
    -0.86
    issance
    -0.76
    slice
    -0.75
    ascript
    -0.74
    Poké
    -0.73
    çĦ
    -0.71
    ļéĨĴ
    -0.71
    unny
    -0.70
    emark
    -0.70
    DragonMagazine
    -0.69
    POSITIVE LOGITS
     retribution
    1.29
     repercussions
    1.23
     lest
    1.13
     repr
    1.13
     retaliation
    1.08
    lessly
    1.05
     imminent
    0.92
     losing
    0.92
     reperc
    0.89
     backlash
    0.88
    Activations Density 0.047%

    No Known Activations