© 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. 2-RES-JB
    11. 8353
    Prev
    Next
    INDEX
    Explanations

    mentions of substances or experiences related to psychedelics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to psychology and psychedelic experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OUS
    -0.78
    thumbnails
    -0.73
    NRS
    -0.73
    Interstitial
    -0.68
     Metatron
    -0.66
    GBT
    -0.66
    Minecraft
    -0.66
     FAR
    -0.65
    DERR
    -0.65
     Thou
    -0.64
    POSITIVE LOGITS
    chedel
    1.41
    ongyang
    0.92
    fen
    0.90
    NetMessage
    0.89
    oking
    0.83
    nergy
    0.82
    atile
    0.81
    kie
    0.81
    psy
    0.81
    veyard
    0.79
    Activations Density 0.013%

    No Known Activations