© 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. 6-RES-JB
    11. 23775
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preparation or anticipation of an upcoming event

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating preparation or anticipation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oret
    -0.80
    ochet
    -0.73
    ãĥĩ
    -0.61
    mes
    -0.61
    bey
    -0.60
    ī
    -0.59
     vein
    -0.59
    ajo
    -0.59
    ues
    -0.59
     halves
    -0.58
    POSITIVE LOGITS
    skirts
    0.90
    ptin
    0.87
    FIELD
    0.78
    roleum
    0.71
    uberty
    0.71
    iatus
    0.71
     ����
    0.70
     unbeliev
    0.70
    ÃįÃį
    0.70
    ubes
    0.70
    Activations Density 0.014%

    No Known Activations