© 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. 4-RES-JB
    11. 7375
    Prev
    Next
    INDEX
    Explanations

    terms related to internal development or processes within an organization

    oai_token-act-pair · gpt-3.5-turbo

    references to internal and external processes or actions

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

    No Comments

    Negative Logits
    ger
    -0.74
     Parenthood
    -0.70
    ties
    -0.69
     Pirate
    -0.67
     Cause
    -0.66
    tons
    -0.65
     Answers
    -0.65
     Victory
    -0.64
     Miracle
    -0.64
     Sylv
    -0.64
    POSITIVE LOGITS
     exting
    0.89
     housed
    0.88
     displaced
    0.86
    ilitary
    0.86
     dispersed
    0.84
    beit
    0.84
     detonated
    0.83
     speaking
    0.82
    duct
    0.82
    hesive
    0.80
    Activations Density 0.036%

    No Known Activations