© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 12900
    Prev
    Next
    INDEX
    Explanations

    words related to risk and fear

    oai_token-act-pair · gpt-3.5-turbo

    themes related to risk assessment and management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    aware, security, taking, reward, management, mongering, based, mistrust, opportunities

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 6 - fear

    No Comments

    Negative Logits
    issance
    -0.81
    çļ
    -0.75
    éĹĺ
    -0.70
    inois
    -0.67
    EEK
    -0.66
    é¾įåĸļ士
    -0.65
    Contents
    -0.64
     caf
    -0.64
    olon
    -0.63
    à¤
    -0.63
    POSITIVE LOGITS
     retribution
    0.76
    ullah
    0.68
     intimidation
    0.67
     avoidance
    0.66
    llah
    0.66
     sqor
    0.65
    xiety
    0.64
    ovi
    0.64
     tremend
    0.63
    gered
    0.63
    Activations Density 0.501%

    No Known Activations