© 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. 8-RES-JB
    11. 6113
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving warnings or alerts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "warned" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anuts
    -0.77
    Interstitial
    -0.74
     ILCS
    -0.74
    mite
    -0.68
    nan
    -0.67
    animate
    -0.66
    OVA
    -0.66
    á
    -0.66
    aredevil
    -0.64
    adesh
    -0.63
    POSITIVE LOGITS
     against
    0.98
    warn
    0.96
     omin
    0.96
    warning
    0.90
     caution
    0.84
     Warn
    0.81
     listeners
    0.78
    ingly
    0.78
     warnings
    0.75
     us
    0.75
    Activations Density 0.025%

    No Known Activations