© 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. 7-RES-JB
    11. 146
    Prev
    Next
    INDEX
    Explanations

    the word stem "continu" followed by various suffixes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to continuity and ongoing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.87
    eah
    -0.76
    Reviewer
    -0.75
    ster
    -0.72
    OST
    -0.72
    ramid
    -0.70
    sters
    -0.69
     WATCHED
    -0.69
    wo
    -0.66
    ifty
    -0.65
    POSITIVE LOGITS
    uations
    0.96
    uously
    0.92
    uous
    0.92
    uation
    0.86
    uity
    0.85
    grain
    0.83
    issance
    0.81
    uality
    0.80
    uum
    0.80
    uing
    0.79
    Activations Density 0.037%

    No Known Activations