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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    6. 4459
    Prev
    Next
    INDEX
    Explanations

    phrases related to putting something in a certain place or position

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to placing or positioning entities in specific contexts or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uracy
    -0.80
    urious
    -0.76
    isan
    -0.70
    artifacts
    -0.67
    scl
    -0.67
    glers
    -0.66
    assadors
    -0.65
    embed
    -0.64
    eni
    -0.64
    xp
    -0.64
    POSITIVE LOGITS
     pedest
    0.83
     jeopardy
    0.79
     disadvantage
    0.70
     throats
    0.64
     humiliating
    0.62
     damn
    0.62
     shame
    0.60
     podium
    0.60
    istine
    0.60
     burner
    0.58
    Activations Density 0.162%

    No Known Activations