© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9974
    Prev
    Next
    INDEX
    Explanations

    phrases related to a decrease or reduction in something

    oai_token-act-pair · gpt-3.5-turbo

    the word "down" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    9999
    -0.79
    ificent
    -0.66
    ature
    -0.64
    aceous
    -0.63
    ista
    -0.62
    000000
    -0.61
    andum
    -0.59
     Pros
    -0.59
    åŃ
    -0.59
    ë
    -0.57
    POSITIVE LOGITS
    graded
    1.45
    grading
    1.32
    LOAD
    1.24
    grades
    1.19
    stairs
    1.16
    played
    1.00
    loaded
    0.98
    pour
    0.95
    hill
    0.92
    sized
    0.91
    Activations Density 0.040%

    No Known Activations