Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 5777
    Prev
    Next
    INDEX
    Explanations

    specific words and phrases that appear at the beginning of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    sentences with a subject-verb structure or specific introductory phrases

    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
     HOU
    -0.71
    SPONSORED
    -0.64
    âĸĪâĸĪ
    -0.64
     PLEASE
    -0.63
    KNOWN
    -0.62
    alert
    -0.61
     TX
    -0.61
     Annotations
    -0.60
     Antioch
    -0.59
     Magnet
    -0.58
    POSITIVE LOGITS
    odore
    0.92
    orem
    0.82
    resa
    0.81
    hester
    0.79
    ories
    0.79
    thren
    0.78
    withstanding
    0.78
    ynchronous
    0.77
    vantage
    0.77
    nsic
    0.76
    Activations Density 0.226%

    No Known Activations