© 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. 9-RES-JB
    11. 4297
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "going down" used in a variety of contexts and topics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¶ħ
    -0.73
    archives
    -0.66
    roma
    -0.63
     Remastered
    -0.61
    cius
    -0.60
    ulsion
    -0.59
    digy
    -0.58
    iliary
    -0.58
    azing
    -0.57
    ota
    -0.57
    POSITIVE LOGITS
     stairs
    1.17
    hill
    1.04
    stairs
    1.03
    graded
    0.98
    grading
    0.97
    LOAD
    0.92
    pour
    0.92
    river
    0.90
     hill
    0.87
    range
    0.82
    Activations Density 0.043%

    No Known Activations