© 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
    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. 3647
    Prev
    Next
    INDEX
    Explanations

    words related to creative concepts or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to ideas and concepts

    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
     Governors
    -0.67
    Aff
    -0.67
    administ
    -0.66
    loads
    -0.65
    aths
    -0.63
    major
    -0.63
    ORD
    -0.63
    don
    -0.63
    Order
    -0.63
    Naz
    -0.63
    POSITIVE LOGITS
    ually
    0.87
     Ideas
    0.83
     hatched
    0.82
     provoking
    0.82
     sugg
    0.80
     ideas
    0.79
     idea
    0.74
     incub
    0.72
     brainstorm
    0.72
     inspir
    0.72
    Activations Density 0.051%

    No Known Activations