© 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. 2-RES-JB
    11. 691
    Prev
    Next
    INDEX
    Explanations

    the word "Media" in different contexts

    oai_token-act-pair · gpt-4-turbo

    media-related terms or references

    oai_token-act-pair · gpt-3.5-turbo

    references to media or media-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ought
    -0.79
    comings
    -0.76
    ranch
    -0.70
     Salvador
    -0.68
    python
    -0.66
     damn
    -0.65
    ãĤ¡
    -0.65
     captcha
    -0.65
    ãĤ¯
    -0.64
    0000000000000000
    -0.63
    POSITIVE LOGITS
    Media
    0.94
     outlets
    0.90
    eval
    0.90
     Matters
    0.89
     Media
    0.88
     Mole
    0.85
    media
    0.85
    medi
    0.79
     mog
    0.77
    fax
    0.77
    Activations Density 0.016%

    No Known Activations