© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13500
    Prev
    Next
    INDEX
    Explanations

    words related to caution or preparation

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate various types of conditions or states, particularly those ending in specific suffixes

    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
    schild
    -0.94
    ufact
    -0.92
    ophon
    -0.86
    ĸļ
    -0.85
    models
    -0.85
    vironment
    -0.82
    IVERS
    -0.80
    soDeliveryDate
    -0.79
    onom
    -0.78
    IRC
    -0.77
    POSITIVE LOGITS
    aneously
    0.99
    aneous
    0.86
    LY
    0.79
     deletion
    0.79
     disclosure
    0.77
    ities
    0.76
     pronoun
    0.74
     derog
    0.74
     easing
    0.73
    ity
    0.72
    Activations Density 0.143%

    No Known Activations