Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 18459
    Prev
    Next
    INDEX
    Explanations

    words related to opposition or resistance towards specific ideologies, groups, or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating opposition or negativity towards various ideological or religious groups

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Nights
    -0.68
     subsequ
    -0.68
     bidder
    -0.67
     blackout
    -0.65
     outage
    -0.64
     chapter
    -0.64
     series
    -0.64
     mailing
    -0.63
     pads
    -0.63
     haze
    -0.63
    POSITIVE LOGITS
    Semitic
    1.12
    establishment
    1.05
    human
    1.05
    environment
    0.98
    liber
    0.97
    consumer
    0.95
    science
    0.95
    productive
    0.94
    athe
    0.93
    democratic
    0.92
    Activations Density 0.058%

    No Known Activations