© 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. 7-RES-JB
    11. 23895
    Prev
    Next
    INDEX
    Explanations

    actions related to manipulating objects

    oai_token-act-pair · gpt-3.5-turbo

    actions related to processing and transforming physical materials or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ooter
    -0.66
    raltar
    -0.66
    nia
    -0.66
    eni
    -0.65
    ieth
    -0.65
    ooters
    -0.65
    cipled
    -0.64
    EStreamFrame
    -0.64
    Merit
    -0.63
    eg
    -0.63
    POSITIVE LOGITS
     them
    1.22
     THEM
    1.05
     accordingly
    1.03
    them
    0.98
     it
    0.83
     therein
    0.78
     Them
    0.74
    itiz
    0.72
     corresponding
    0.71
     thereafter
    0.69
    Activations Density 0.503%

    No Known Activations