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. 8-RES-JB
    6. 4363
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "Many of" is followed by a plural noun or pronoun

    oai_token-act-pair · gpt-3.5-turbo

    the repetitive use of the phrase "many of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     agre
    -0.72
    ahime
    -0.69
     cape
    -0.68
     unfocusedRange
    -0.66
    berus
    -0.65
     lapt
    -0.65
    ovember
    -0.63
    MpServer
    -0.63
    ĸļ
    -0.61
     buffet
    -0.60
    POSITIVE LOGITS
    those
    0.84
     those
    0.84
     us
    0.80
     these
    0.78
     respondents
    0.73
     whom
    0.73
     sudden
    0.70
     them
    0.69
    these
    0.68
     our
    0.67
    Activations Density 0.085%

    No Known Activations