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. 4-RES-JB
    6. 9808
    Prev
    Next
    INDEX
    Explanations

    words related to psychedelic substances, especially psilocybin mushrooms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to psychoactive substances and their effects

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

    No Comments

    Negative Logits
     sexes
    -0.71
    enburg
    -0.69
    LER
    -0.68
    ieri
    -0.63
     representation
    -0.63
     Represent
    -0.62
    enders
    -0.62
    IAN
    -0.61
     builders
    -0.60
    bread
    -0.60
    POSITIVE LOGITS
    etsk
    0.83
    aml
    0.82
    ihu
    0.82
    toc
    0.80
    ä
    0.78
    aukee
    0.77
    prus
    0.75
    anism
    0.74
    ocy
    0.74
    oshenko
    0.74
    Activations Density 0.030%

    No Known Activations