© 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. 11085
    Prev
    Next
    INDEX
    Explanations

    phrases related to progression or advancement along a path or journey

    oai_token-act-pair · gpt-3.5-turbo

    common locations or paths described in a narrative context

    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
    thood
    -0.95
    OUP
    -0.67
    Mom
    -0.66
     constitu
    -0.64
    OHN
    -0.64
    addon
    -0.64
    CVE
    -0.64
    RIC
    -0.62
    PLIC
    -0.62
    RM
    -0.62
    POSITIVE LOGITS
     periphery
    0.94
     sidelines
    0.89
     path
    0.82
     seams
    0.79
     rest
    0.78
     usual
    0.77
     same
    0.77
     entirety
    0.71
     opposite
    0.69
    lyak
    0.69
    Activations Density 0.056%

    No Known Activations