© 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. 8-RES-JB
    11. 16850
    Prev
    Next
    INDEX
    Explanations

    phrases related to religious and spiritual themes and concepts

    oai_token-act-pair · gpt-3.5-turbo

    expressions of resolve and declarations of intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anecd
    -0.65
    umably
    -0.60
     clustered
    -0.60
     headlined
    -0.58
     Collider
    -0.58
    entially
    -0.58
     turnover
    -0.57
    ãĤ´ãĥ³
    -0.57
     unsurprisingly
    -0.57
     marquee
    -0.57
    POSITIVE LOGITS
     thou
    1.01
     thy
    0.99
     repent
    0.93
     ye
    0.91
     everlasting
    0.91
     thee
    0.90
     shall
    0.89
     Almighty
    0.88
     righteousness
    0.87
     Thou
    0.87
    Activations Density 1.148%

    No Known Activations