© 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. 1388
    Prev
    Next
    INDEX
    Explanations

    words related to strength, power, or intensity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'r'

    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
    isSpecialOrderable
    -0.89
    etheless
    -0.85
    SPONSORED
    -0.78
    channelAvailability
    -0.77
    elist
    -0.71
    emark
    -0.66
    ophone
    -0.65
    abase
    -0.65
    theless
    -0.64
    metics
    -0.64
    POSITIVE LOGITS
     r
    3.12
     rh
    1.39
    r
    1.38
     R
    1.36
     ram
    1.31
     l
    1.28
     t
    1.27
     rc
    1.24
     ro
    1.22
     rs
    1.22
    Activations Density 0.023%

    No Known Activations