© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    6. 15054
    Prev
    Next
    INDEX
    Explanations

    names consisting of the word "Abdel"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Abdel."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tycoon
    -0.83
     UNIVERS
    -0.78
     Bermuda
    -0.77
     Leap
    -0.74
     Scotch
    -0.71
     Scots
    -0.71
    nz
    -0.68
     Scottish
    -0.68
     Remastered
    -0.68
     Eclipse
    -0.67
    POSITIVE LOGITS
    afia
    1.01
     Abdel
    0.94
     Rahman
    0.81
    inia
    0.79
    irez
    0.78
    der
    0.77
    azard
    0.76
    rahim
    0.75
     challeng
    0.74
    bas
    0.74
    Activations Density 0.004%

    No Known Activations