© 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. 10-RES-JB
    11. 21817
    Prev
    Next
    INDEX
    Explanations

    time-related events or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to danger or risk situations

    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
    Had
    -0.93
    tained
    -0.89
     hindsight
    -0.84
    emed
    -0.83
     interacted
    -0.74
     retrospect
    -0.74
    aughed
    -0.73
    oided
    -0.71
    Was
    -0.71
    orted
    -0.70
    POSITIVE LOGITS
     threatens
    1.12
     will
    1.09
     intends
    1.06
     awaits
    0.98
     are
    0.95
     wants
    0.95
     intend
    0.92
     threaten
    0.90
     scares
    0.90
     expects
    0.90
    Activations Density 0.934%

    No Known Activations