© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 10113
    Prev
    Next
    INDEX
    Explanations

    words related to seeking or finding shelter or protection

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "refuge" in various contexts

    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
    oths
    -0.79
    ONES
    -0.78
    scope
    -0.72
    FK
    -0.71
    ammy
    -0.70
     curv
    -0.69
    thin
    -0.68
    asts
    -0.68
    oth
    -0.67
    lass
    -0.67
    POSITIVE LOGITS
     refuge
    1.20
     Refuge
    0.95
    ctuary
    0.91
    ashtra
    0.76
    ilitation
    0.73
     sanctuary
    0.70
     seeker
    0.70
    ãĥķãĤ¡
    0.69
     encl
    0.69
    gur
    0.68
    Activations Density 0.012%

    No Known Activations