© 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. 6-RES-JB
    11. 10739
    Prev
    Next
    INDEX
    Explanations

    prepositions and directions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and words indicating relationships or direction

    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
    soever
    -0.56
    (*
    -0.55
     @@
    -0.49
     unwelcome
    -0.45
     preferred
    -0.44
     GS
    -0.43
     UNCLASSIFIED
    -0.43
     âĢİ
    -0.43
     desired
    -0.43
     unemploy
    -0.42
    POSITIVE LOGITS
    cephal
    0.59
    pless
    0.58
    ueller
    0.56
    urnal
    0.56
    olen
    0.53
    ovi
    0.53
    odan
    0.52
    arton
    0.51
    ãĥ´
    0.51
    inav
    0.51
    Activations Density 1.357%

    No Known Activations