© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 18574
    Prev
    Next
    INDEX
    Explanations

    words related to directions and positions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gender and directional or positional descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gone
    -0.81
    jan
    -0.78
    atl
    -0.78
    Joy
    -0.74
    stros
    -0.74
    ogi
    -0.72
    mud
    -0.72
    afety
    -0.71
    atis
    -0.71
    tyard
    -0.70
    POSITIVE LOGITS
     alike
    1.43
     respectively
    1.31
     depending
    1.14
     versions
    0.91
     striped
    0.86
    depending
    0.82
     administrations
    0.81
     coasts
    0.80
     grades
    0.79
     editions
    0.78
    Activations Density 0.292%

    No Known Activations