© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 17308
    Prev
    Next
    INDEX
    Explanations

    references to the hallucinogenic plant Ayahuasca

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the psychoactive plant Ayahuasca

    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
    piece
    -0.64
     Indust
    -0.64
     fixation
    -0.63
     vein
    -0.63
    */(
    -0.62
    âĶģ
    -0.62
     Handling
    -0.61
    LAB
    -0.58
     Teams
    -0.58
    meal
    -0.58
    POSITIVE LOGITS
    asca
    1.41
    ahu
    1.35
    isance
    1.03
    aii
    1.00
    ahah
    0.96
    ulhu
    0.92
    acan
    0.88
    actus
    0.87
    estic
    0.86
    atl
    0.86
    Activations Density 0.007%

    No Known Activations