© 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. 3-RES-JB
    11. 10813
    Prev
    Next
    INDEX
    Explanations

    terms related to infestation and overwhelming quantities

    oai_token-act-pair · gpt-3.5-turbo

    words related to infestation or overwhelming situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peer
    -0.78
    ©¶æ
    -0.73
    neg
    -0.73
    raq
    -0.72
    aroo
    -0.66
     compr
    -0.66
     partName
    -0.66
    ben
    -0.66
     srfAttach
    -0.61
    usercontent
    -0.59
    POSITIVE LOGITS
    ious
    0.81
    ings
    0.78
    redients
    0.75
    iously
    0.75
     dots
    0.73
    uzz
    0.71
    acers
    0.70
    enza
    0.70
    eston
    0.69
    agues
    0.69
    Activations Density 0.116%

    No Known Activations