© 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. 10-RES-JB
    11. 5858
    Prev
    Next
    INDEX
    Explanations

    phrases related to future actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    the verb "be" and its various contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oops
    -0.81
    olitics
    -0.79
     ILCS
    -0.74
    ossus
    -0.71
    oras
    -0.65
    KEN
    -0.65
    osate
    -0.64
     Stability
    -0.64
    berus
    -0.64
    adena
    -0.64
    POSITIVE LOGITS
     releasing
    1.15
     attending
    1.13
     updating
    1.12
     submitting
    1.11
     contacting
    1.10
     doing
    1.09
     conducting
    1.06
     able
    1.05
     discussing
    1.04
     returning
    1.04
    Activations Density 0.097%

    No Known Activations