© 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. 6-RES-JB
    11. 1695
    Prev
    Next
    INDEX
    Explanations

    words related to electronic devices, specifically "Mic" as part of a product or brand name

    oai_token-act-pair · gpt-3.5-turbo

    references to the brand "Micromax" or related products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENGTH
    -0.77
    tenance
    -0.72
    ACTED
    -0.72
    mberg
    -0.71
    ãĤĤ
    -0.71
    hood
    -0.68
     Dull
    -0.65
     Unified
    -0.65
     Directorate
    -0.65
    ĪĴ
    -0.62
    POSITIVE LOGITS
    HAEL
    1.11
    rodu
    1.11
    helle
    1.06
    ropolitan
    1.06
    roman
    1.04
    ron
    1.00
    rom
    0.99
    ross
    0.98
    rones
    0.98
    eli
    0.95
    Activations Density 0.026%

    No Known Activations