© 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. 8-RES-JB
    11. 22566
    Prev
    Next
    INDEX
    Explanations

    words related to personal relationships and emotions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with intimacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    corn
    -0.79
    soDeliveryDate
    -0.77
    udeb
    -0.74
    enic
    -0.71
    tower
    -0.69
    sup
    -0.69
    dule
    -0.68
    ————
    -0.67
    deen
    -0.63
     fielded
    -0.63
    POSITIVE LOGITS
     intimate
    0.79
     sensations
    0.78
    voy
    0.72
     pleasure
    0.72
    ivities
    0.70
    metry
    0.70
     witnessing
    0.69
    phys
    0.69
     tactile
    0.69
     IMAGES
    0.69
    Activations Density 0.118%

    No Known Activations