© 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. 24113
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Ed" combined with numbers representing a specific Ed identified in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ed" in various contexts

    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
    ¬¼
    -0.76
    TY
    -0.70
    cffffcc
    -0.70
    =-=-
    -0.69
    ãģį
    -0.67
    EStreamFrame
    -0.64
    externalActionCode
    -0.63
    Ĥİ
    -0.63
    ���
    -0.62
    ����
    -0.62
    POSITIVE LOGITS
    ifice
    1.14
    gew
    1.10
    itions
    1.08
    pires
    1.07
    gewater
    1.01
    icion
    1.00
    monton
    0.99
    gel
    0.99
    uce
    0.97
    ges
    0.97
    Activations Density 0.009%

    No Known Activations