© 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. 13925
    Prev
    Next
    INDEX
    Explanations

    phrases related to causing significant impact or change

    oai_token-act-pair · gpt-3.5-turbo

    metaphors and expressions related to change and transition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Landing
    -0.62
    ailability
    -0.59
    ãĤ½
    -0.59
    gement
    -0.56
    inia
    -0.55
    anta
    -0.54
    ãģ¾
    -0.54
    annot
    -0.53
    ãĥĺ
    -0.53
    ãĥģ
    -0.53
    POSITIVE LOGITS
    iest
    0.89
    UTH
    0.80
     nicely
    0.77
     wisely
    0.75
     convinc
    0.73
     prematurely
    0.73
     correctly
    0.73
     anew
    0.72
    enium
    0.72
    elight
    0.72
    Activations Density 0.329%

    No Known Activations