© 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. 7-RES-JB
    11. 9484
    Prev
    Next
    INDEX
    Explanations

    expressions indicating the likelihood of future events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "will" to identify future-oriented statements or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amps
    -0.62
     Sandwich
    -0.61
    ãĤ´ãĥ³
    -0.61
    JD
    -0.61
    engineering
    -0.61
    Plan
    -0.60
    quished
    -0.60
    Reporting
    -0.59
     Romeo
    -0.59
    ocular
    -0.59
    POSITIVE LOGITS
     inevitably
    1.19
     gladly
    1.19
     undoubtedly
    1.18
     doubtless
    1.15
     be
    1.15
     surely
    1.10
     likely
    1.06
     eventually
    1.04
     probably
    1.02
     continue
    1.00
    Activations Density 0.220%

    No Known Activations