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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 6626
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions and preferences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of public opinion and sentiment towards a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     latter
    -0.73
    ornings
    -0.72
    ropolitan
    -0.70
     respectively
    -0.66
    adies
    -0.64
    eteen
    -0.58
    aina
    -0.58
    nery
    -0.57
    wife
    -0.56
    ENA
    -0.56
    POSITIVE LOGITS
     SCP
    0.82
    ratom
    0.79
     graphene
    0.74
     Xperia
    0.74
    DragonMagazine
    0.74
     bitcoin
    0.74
     OnePlus
    0.71
    bitcoin
    0.71
    Torrent
    0.70
     Ripple
    0.69
    Activations Density 1.416%

    No Known Activations