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

    Neuronpedia

    Jacobian LensNEW
    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. 6885
    Prev
    Next
    INDEX
    Explanations

    phrases related to sipping a drink

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions involving drinking and hospitality

    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
     optic
    -0.78
     oxide
    -0.70
    pex
    -0.68
     durable
    -0.67
     wrench
    -0.66
    ascus
    -0.65
     rubble
    -0.65
     converter
    -0.64
     obliter
    -0.64
     Compton
    -0.64
    POSITIVE LOGITS
    ATURES
    0.85
     roles
    0.83
    chair
    0.81
    goers
    0.81
    chairs
    0.79
    igraph
    0.76
    ATURE
    0.76
     seated
    0.75
     Cosponsors
    0.75
    mans
    0.74
    Activations Density 0.143%

    No Known Activations