© 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. 9-RES-JB
    11. 20749
    Prev
    Next
    INDEX
    Explanations

    future tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    future conditional phrases or verbs indicating intention or possibility

    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
     adolesc
    -0.76
    foreseen
    -0.67
    fortable
    -0.64
    ifter
    -0.62
     Tayyip
    -0.62
     Crunch
    -0.60
     receptions
    -0.59
     Revis
    -0.59
    annis
    -0.58
    ITED
    -0.57
    POSITIVE LOGITS
     surely
    1.19
     undoubtedly
    1.11
     probably
    1.10
     likely
    1.08
     certainly
    1.07
     definitely
    1.07
     automatically
    1.04
     be
    1.02
     doubtless
    0.98
     gladly
    0.98
    Activations Density 0.199%

    No Known Activations