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. 7-RES-JB
    6. 14999
    Prev
    Next
    INDEX
    Explanations

    words related to personal narratives or storytelling

    oai_token-act-pair · gpt-3.5-turbo

    discussions about social issues faced by individuals and communities

    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
    §
    -0.68
    tch
    -0.64
    Ń·
    -0.63
    ¿½
    -0.55
    bris
    -0.54
    whatever
    -0.53
    lycer
    -0.53
    Ļ
    -0.51
    arms
    -0.50
    İ
    -0.50
    POSITIVE LOGITS
     misconceptions
    0.65
     myths
    0.55
     differently
    0.54
     hypocrisy
    0.53
     heroism
    0.53
     topics
    0.53
     transgender
    0.52
     pitfalls
    0.51
     contemporary
    0.51
     firsthand
    0.51
    Activations Density 1.309%

    No Known Activations