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. 6-RES-JB
    6. 23943
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to political parties and sides in a debate or election context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aca
    -0.71
    athetic
    -0.70
    sections
    -0.69
     Dialogue
    -0.67
    atible
    -0.66
    ect
    -0.65
    rome
    -0.65
    hips
    -0.65
    anth
    -0.65
    otti
    -0.63
    POSITIVE LOGITS
     claim
    0.90
     successfully
    0.79
     unsuccessfully
    0.72
     capitalize
    0.70
     contends
    0.69
    ãĥ³ãĤ¸
    0.68
     contend
    0.67
     control
    0.67
     advertise
    0.66
     possession
    0.65
    Activations Density 1.074%

    No Known Activations