© 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. 3659
    Prev
    Next
    INDEX
    Explanations

    mentions of marine creatures, specifically jellyfish

    oai_token-act-pair · gpt-3.5-turbo

    mentions of jellyfish

    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
    PsyNetMessage
    -0.74
     conclud
    -0.71
    Þ
    -0.68
    itatively
    -0.67
    raine
    -0.65
     estab
    -0.63
    taboola
    -0.63
     referen
    -0.62
    iqu
    -0.61
    senal
    -0.61
    POSITIVE LOGITS
    fish
    1.26
    Fish
    0.90
     Islands
    0.86
    bowl
    0.85
    erella
    0.81
     ponds
    0.80
     crabs
    0.79
    tails
    0.77
     larvae
    0.76
    ectomy
    0.75
    Activations Density 0.008%

    No Known Activations