© 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. 2031
    Prev
    Next
    INDEX
    Explanations

    words related to events happening one after another

    oai_token-act-pair · gpt-3.5-turbo

    references to events that follow a specific occurrence or action

    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
    tics
    -0.76
    gged
    -0.74
    nut
    -0.72
    eno
    -0.70
    yers
    -0.68
    friend
    -0.68
    tek
    -0.68
    aiman
    -0.65
    Bay
    -0.65
    mberg
    -0.64
    POSITIVE LOGITS
     generations
    0.87
     subsequent
    0.79
     unsuccessful
    0.74
     fallout
    0.72
    itized
    0.71
     CLSID
    0.70
    gradation
    0.69
     waves
    0.69
     erosion
    0.69
     revisions
    0.68
    Activations Density 0.047%

    No Known Activations