© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 24123
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names or entities mentioned, particularly the name "Morton" and the initials "ND."

    oai_token-act-pair · gpt-3.5-turbo

    names of people and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elaide
    -0.98
    encers
    -0.90
    fax
    -0.88
    manship
    -0.84
    perors
    -0.83
    beat
    -0.82
    âĸ¬
    -0.81
    loo
    -0.78
    encer
    -0.76
     Bulldogs
    -0.74
    POSITIVE LOGITS
    umber
    0.80
    quist
    0.78
     Morton
    0.72
     ç¥ŀ
    0.71
     Dillon
    0.71
    hyde
    0.70
     Brach
    0.70
     unborn
    0.67
     Kinder
    0.63
     NR
    0.63
    Activations Density 0.016%

    No Known Activations