© 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. 7-RES-JB
    11. 1730
    Prev
    Next
    INDEX
    Explanations

    words that indicate agreement or similarity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "alike" used in various contexts to indicate similarity or commonality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.74
     Ãĸ
    -0.65
    opian
    -0.65
    Georg
    -0.64
    Pan
    -0.63
    omatic
    -0.62
    OLOG
    -0.62
     Shang
    -0.61
     Nurs
    -0.60
    ohyd
    -0.60
    POSITIVE LOGITS
     alike
    1.28
    lihood
    0.84
     rejoice
    0.83
    soever
    0.82
     greets
    0.72
    ials
    0.72
     sexes
    0.71
    isSpecialOrderable
    0.71
    WHERE
    0.71
     eager
    0.70
    Activations Density 0.028%

    No Known Activations