© 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. 7-RES-JB
    6. 17099
    Prev
    Next
    INDEX
    Explanations

    mentions of disturbances or things that are disturbing

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to disturbance or distress

    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
    Not in Any Lists

    No Comments

    Negative Logits
    uay
    -0.82
    ardi
    -0.79
    hler
    -0.74
    arde
    -0.74
    tin
    -0.73
    á
    -0.73
    veland
    -0.72
    elsen
    -0.71
    HER
    -0.70
    cellence
    -0.70
    POSITIVE LOGITS
    ingly
    0.89
     Trend
    0.67
     signals
    0.66
     behaviour
    0.66
     Enlightenment
    0.66
     behaviours
    0.64
     Territories
    0.62
     Geo
    0.61
     behaviors
    0.60
     neighbours
    0.60
    Activations Density 0.064%

    No Known Activations