Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 17471
    Prev
    Next
    INDEX
    Explanations

    words related to the term "Mach" along with accompanying numeric values that are specific to speed indicators

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Mach" followed by varying numerical values, likely related to speed measurements

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

    No Comments

    Negative Logits
    SHIP
    -0.76
    payer
    -0.69
    0000000000000000
    -0.68
     Citizens
    -0.67
     Vive
    -0.66
     Physicians
    -0.64
    etheless
    -0.63
    ãģ®éŃĶ
    -0.63
     Defenders
    -0.63
     EDITION
    -0.63
    POSITIVE LOGITS
    inery
    1.19
    Mach
    0.90
     Mach
    0.90
    insk
    0.85
    inations
    0.82
    ineries
    0.81
    omet
    0.77
    uria
    0.76
    otomy
    0.76
    itud
    0.73
    Activations Density 0.008%

    No Known Activations