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. 9254
    Prev
    Next
    INDEX
    Explanations

    positively framed phrases related to trying or attempting something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to taking chances or trying something new

    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
    ceivable
    -0.70
     unaware
    -0.68
    ILE
    -0.67
    ZI
    -0.66
     knowledgeable
    -0.64
    raine
    -0.63
    URES
    -0.63
    cigarettes
    -0.61
    avid
    -0.60
    URE
    -0.60
    POSITIVE LOGITS
     IPO
    0.78
     precedence
    0.74
    Origin
    0.73
     bloom
    0.72
     resurgence
    0.72
     shine
    0.72
     foothold
    0.71
     dominance
    0.70
     evolutionary
    0.70
     Drift
    0.70
    Activations Density 1.065%

    No Known Activations