© 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. 4-RES-JB
    11. 425
    Prev
    Next
    INDEX
    Explanations

    words related to uncontrollable emotional outbursts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "tantrum" and related contexts of anger or frustration

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

    No Comments

    Negative Logits
    endif
    -0.71
     seeded
    -0.71
    ombies
    -0.65
     endif
    -0.64
    ournals
    -0.64
     Donation
    -0.63
    ipeg
    -0.61
    zzo
    -0.60
    ffiti
    -0.60
    Featured
    -0.60
    POSITIVE LOGITS
     tant
    1.48
    amount
    1.00
     Tant
    0.97
    urn
    0.86
    iques
    0.85
    ras
    0.85
    alus
    0.85
    emonium
    0.84
    rums
    0.84
    rance
    0.80
    Activations Density 0.013%

    No Known Activations