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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21546
    Prev
    Next
    INDEX
    Explanations

    gender-specific words related to women

    oai_token-act-pair · gpt-3.5-turbo

    topics related to social issues and governance

    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
     oneself
    -0.84
     Hond
    -0.65
     TX
    -0.64
     Maryland
    -0.63
     myself
    -0.61
     FedEx
    -0.61
    SON
    -0.59
     Crew
    -0.59
    Else
    -0.59
     Singer
    -0.58
    POSITIVE LOGITS
     population
    0.94
    iest
    0.93
     heritage
    0.87
     woes
    0.86
     monarchy
    0.81
     inhabitants
    0.79
     populace
    0.78
     economy
    0.77
     coastline
    0.76
     workforce
    0.76
    Activations Density 0.550%

    No Known Activations