© 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. 7-RES-JB
    11. 24564
    Prev
    Next
    INDEX
    Explanations

    people's names starting with "Em"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Em" with high frequency, likely related to people or entities in the context provided

    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
    etheless
    -0.79
    ãģį
    -0.68
     counter
    -0.67
     PRESS
    -0.67
     RIS
    -0.66
    WARE
    -0.66
     sight
    -0.66
     plag
    -0.64
     Learns
    -0.64
    WAYS
    -0.63
    POSITIVE LOGITS
    acher
    1.27
    isha
    1.14
    igl
    1.09
    iman
    1.07
    iber
    1.05
    anta
    1.05
    oran
    1.00
    agg
    1.00
    uid
    1.00
    atz
    0.98
    Activations Density 0.177%

    No Known Activations