Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 23944
    Prev
    Next
    INDEX
    Explanations

    mentions of psychedelic substances and related experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to psychedelic substances and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tower
    -0.75
    Avg
    -0.67
    aldi
    -0.65
    igers
    -0.64
    Ranked
    -0.62
    MpServer
    -0.61
     Chiefs
    -0.61
    kus
    -0.60
    parts
    -0.60
    Score
    -0.60
    POSITIVE LOGITS
    chedel
    1.34
     halluc
    1.02
     mushrooms
    1.00
     LSD
    0.96
     drugs
    0.95
    osis
    0.95
    stasy
    0.95
     psychedelic
    0.87
     psychedel
    0.87
     drug
    0.85
    Activations Density 0.079%

    No Known Activations