© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8733
    Prev
    Next
    INDEX
    Explanations

    words related to creation or formation, such as 'form', 'create', 'produce'

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the process of creation or formation

    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
     opin
    -0.73
    intend
    -0.73
    auth
    -0.72
    Parents
    -0.71
    review
    -0.68
    blogspot
    -0.68
    author
    -0.67
    speaking
    -0.66
    tesy
    -0.66
    Availability
    -0.66
    POSITIVE LOGITS
     makeshift
    0.94
     usable
    0.89
     anew
    0.81
    ãĤ©
    0.81
     sculptures
    0.80
     beautiful
    0.80
     a
    0.78
     spherical
    0.76
     reversible
    0.75
     permanent
    0.75
    Activations Density 0.206%

    No Known Activations