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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 1027
    Prev
    Next
    INDEX
    Explanations

    phrases related to psychological or mental health terms, specifically those related to psychoactive substances and practices

    oai_token-act-pair · gpt-3.5-turbo

    terms related to psychology and psychoactive 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
    20439
    -0.72
    ICAN
    -0.71
     dots
    -0.64
     legends
    -0.64
     graft
    -0.63
    MENTS
    -0.62
     perfection
    -0.61
     inaccur
    -0.61
     repetition
    -0.61
    ||||
    -0.61
    POSITIVE LOGITS
    stown
    0.94
    ker
    0.89
    ze
    0.81
     Sack
    0.81
    sth
    0.80
    egu
    0.79
    cott
    0.79
    ega
    0.77
    ven
    0.74
    alf
    0.72
    Activations Density 0.026%

    No Known Activations