© 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. 6-RES-JB
    11. 17708
    Prev
    Next
    INDEX
    Explanations

    prepositions or prepositional phrases related to relationships between objects or actions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases related to locations or conditions within 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
    çĶ°
    -0.94
    NES
    -0.83
    é¾įåĸļ士
    -0.81
    ãĤ«
    -0.76
    Ô
    -0.75
    ENTS
    -0.74
    iHUD
    -0.73
    IFE
    -0.73
    BUG
    -0.72
    00007
    -0.72
    POSITIVE LOGITS
     various
    0.95
     different
    0.90
     specific
    0.82
     selectively
    0.80
     varying
    0.75
     afar
    0.73
     themselves
    0.70
    outed
    0.70
     other
    0.69
     either
    0.68
    Activations Density 0.504%

    No Known Activations