© 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. 17811
    Prev
    Next
    INDEX
    Explanations

    words related to making a task more difficult or easier, depending on the context

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating difficulty or ease regarding tasks or situations

    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
    chn
    -0.71
     Flags
    -0.63
     SUM
    -0.62
     chang
    -0.62
    iche
    -0.61
    WER
    -0.60
    ODY
    -0.59
     LOVE
    -0.59
    aret
    -0.58
    Introduced
    -0.58
    POSITIVE LOGITS
    enged
    0.74
    imaru
    0.69
     enforce
    0.67
    aneously
    0.67
     prey
    0.67
     unwanted
    0.66
    itary
    0.66
    anced
    0.63
    forced
    0.62
     rout
    0.62
    Activations Density 0.063%

    No Known Activations