© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 8333
    Prev
    Next
    INDEX
    Explanations

    phrases related to falling or decline

    oai_token-act-pair · gpt-3.5-turbo

    words related to "calling" or similar phonetic constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Third
    -0.71
     Tribe
    -0.67
     Social
    -0.64
     likeness
    -0.63
     professionally
    -0.63
     Second
    -0.63
     nude
    -0.62
     creed
    -0.62
     honored
    -0.62
     prose
    -0.62
    POSITIVE LOGITS
    alling
    4.61
    alled
    3.00
    alls
    2.17
    aling
    1.99
    ALL
    1.40
    all
    1.36
    aled
    1.34
    als
    1.27
    arching
    1.18
    ALS
    1.13
    Activations Density 0.010%

    No Known Activations