© 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 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. 11-RES-JB
    11. 7486
    Prev
    Next
    INDEX
    Explanations

    words related to direction or descent

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of descending or falling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aceous
    -0.59
    okemon
    -0.58
    isd
    -0.56
     avail
    -0.55
    ë
    -0.55
    INO
    -0.53
    archives
    -0.53
    ÙIJ
    -0.52
    ificent
    -0.52
    acity
    -0.51
    POSITIVE LOGITS
    grading
    1.23
    graded
    1.22
    LOAD
    1.11
    grades
    1.10
     stairs
    1.09
    stairs
    1.06
    river
    1.00
    hill
    0.95
    sized
    0.83
    wind
    0.82
    Activations Density 0.066%

    No Known Activations