© 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. 1-RES-JB
    11. 3730
    Prev
    Next
    INDEX
    Explanations

    dates expressed in the format of 'month, day, year'

    oai_token-act-pair · gpt-3.5-turbo

    numbers and numerical data, particularly those related to historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.53
    ĵĺ
    -0.51
     exha
    -0.46
    etheless
    -0.42
     pse
    -0.41
     tremend
    -0.41
     tradem
    -0.40
     mathemat
    -0.40
     newcom
    -0.39
     satell
    -0.39
    POSITIVE LOGITS
     onward
    0.41
    GV
    0.39
    ividual
    0.38
     onwards
    0.37
    tenance
    0.37
    èĢħ
    0.36
    uart
    0.36
    3000
    0.36
    代
    0.36
    083
    0.36
    Activations Density 1.617%

    No Known Activations