© 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 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. 16604
    Prev
    Next
    INDEX
    Explanations

    contractions in sentences

    oai_token-act-pair · gpt-3.5-turbo

    contractions referring to possessive or indicative phrases

    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
    imeter
    -0.68
    heid
    -0.67
    rawdownloadcloneembedreportprint
    -0.63
    ãĤ´ãĥ³
    -0.62
    icka
    -0.62
    estial
    -0.61
    estern
    -0.61
    ics
    -0.59
    imeters
    -0.59
    sch
    -0.57
    POSITIVE LOGITS
     why
    1.10
     okay
    0.98
    why
    0.96
     exactly
    0.90
     understandable
    0.90
     reflected
    0.89
     fine
    0.89
     precisely
    0.88
     OK
    0.83
     unacceptable
    0.82
    Activations Density 0.086%

    No Known Activations