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. 11-RES-JB
    6. 17890
    Prev
    Next
    INDEX
    Explanations

    phrases related to the fictional character "Phoebe" accompanied by medical conditions, speculative technology, or financial terms

    oai_token-act-pair · gpt-3.5-turbo

    the mention of "Ph" as a recurring term, likely denoting a reference or theme throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fit
    -0.77
    éĹĺ
    -0.73
    */(
    -0.66
     stroke
    -0.66
     fitting
    -0.66
     writ
    -0.65
     tongues
    -0.63
     CPS
    -0.62
     Hitman
    -0.61
    CLASSIFIED
    -0.61
    POSITIVE LOGITS
    antom
    1.46
    osph
    1.44
    obia
    1.43
    ysics
    1.38
    obos
    1.34
    araoh
    1.33
    oenix
    1.31
    allic
    1.29
    alan
    1.26
    ilipp
    1.25
    Activations Density 0.034%

    No Known Activations