© 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. 11-RES-JB
    11. 9990
    Prev
    Next
    INDEX
    Explanations

    words related to positive traits or outcomes, such as inspiration, action, power, comfort, support, success, stability, innovation, equality, and comfort

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to growth, support, and positive change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akedown
    -0.71
     Avenger
    -0.65
     Ri
    -0.65
     Founding
    -0.64
    ofi
    -0.62
     Revolutionary
    -0.61
    ortium
    -0.61
     Mash
    -0.60
     salute
    -0.59
     dataset
    -0.58
    POSITIVE LOGITS
     wherever
    1.08
    ously
    1.00
    ably
    0.99
     elsewhere
    0.97
    boats
    0.93
    lessly
    0.92
     everywhere
    0.91
    strings
    0.91
    fully
    0.88
    cards
    0.85
    Activations Density 0.388%

    No Known Activations