© 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. 3777
    Prev
    Next
    INDEX
    Explanations

    phrases related to anticipation or holding back

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "holding" in various contexts

    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
    esar
    -0.78
    lli
    -0.72
    ffe
    -0.65
     Everywhere
    -0.64
     Adventures
    -0.64
    urus
    -0.62
    yle
    -0.61
    γ
    -0.61
    ES
    -0.59
    DIT
    -0.58
    POSITIVE LOGITS
     ransom
    1.06
     hostage
    1.04
     accountable
    0.95
     breath
    0.78
     veto
    0.76
     reins
    0.75
     precedence
    0.73
     scissors
    0.72
     breaths
    0.70
     hostages
    0.67
    Activations Density 0.153%

    No Known Activations