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. 1-RES-JB
    6. 19734
    Prev
    Next
    INDEX
    Explanations

    phrases related to psychedelic experiences or substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to psychology and psychedelic substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    advertisement
    -0.71
     Metatron
    -0.69
     FAR
    -0.69
    ILA
    -0.69
    OUS
    -0.68
    GBT
    -0.66
    arium
    -0.64
    NRS
    -0.62
    thumbnails
    -0.61
     homophobic
    -0.60
    POSITIVE LOGITS
    chedel
    1.29
    fen
    1.02
    psy
    1.02
    NetMessage
    0.99
    nergy
    0.86
     Psy
    0.84
    ongyang
    0.81
    cture
    0.79
    kie
    0.78
    oking
    0.78
    Activations Density 0.008%

    No Known Activations