© 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. 11-RES-JB
    6. 6446
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical placement or arrangement, such as things being bolted under, drilled in, set over, or located beneath

    oai_token-act-pair · gpt-3.5-turbo

    spatial relationships and positioning of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Polit
    -0.58
    Hunt
    -0.57
     rewritten
    -0.56
    RESULTS
    -0.55
    UPDATE
    -0.55
    Attempt
    -0.54
    Registered
    -0.53
    hess
    -0.52
    Thousands
    -0.52
    piracy
    -0.51
    POSITIVE LOGITS
     each
    1.02
    neath
    0.97
     the
    0.95
     your
    0.89
     whichever
    0.86
     underside
    0.85
     srfAttach
    0.82
     corners
    0.81
     perpendicular
    0.80
     circumference
    0.78
    Activations Density 0.240%

    No Known Activations