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. 9-RES-JB
    6. 7700
    Prev
    Next
    INDEX
    Explanations

    phrases related to important social and political issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant societal issues and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ETF
    -0.69
    âĸij
    -0.65
    ACP
    -0.65
    has
    -0.61
    claimer
    -0.60
    Alias
    -0.60
    sterdam
    -0.60
    SPA
    -0.59
    raper
    -0.59
    taboola
    -0.59
    POSITIVE LOGITS
     happen
    0.92
     unfold
    0.88
     involve
    0.80
     mortals
    0.78
     agendas
    0.77
     arise
    0.77
     occur
    0.75
     themselves
    0.74
     retrospect
    0.74
     hindsight
    0.70
    Activations Density 0.621%

    No Known Activations