© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9603
    Prev
    Next
    INDEX
    Explanations

    terms related to spatial or physical positioning, particularly focusing on the front or in close proximity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize positioning or proximity

    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
     Nanto
    -0.82
    bern
    -0.73
    ofi
    -0.71
    ilver
    -0.70
    umn
    -0.68
    iple
    -0.67
    RED
    -0.67
    GREEN
    -0.66
    upper
    -0.65
    ucci
    -0.65
    POSITIVE LOGITS
     prelim
    0.73
    edly
    0.70
     toile
    0.63
    ¶ħ
    0.61
     apolog
    0.61
     Leilan
    0.61
    xual
    0.61
     instruction
    0.60
    pter
    0.59
     hallucinations
    0.59
    Activations Density 0.075%

    No Known Activations