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. 10-RES-JB
    6. 20250
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the timeline or progression of events from beginning to end

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogie
    -0.76
    MODE
    -0.73
    reau
    -0.68
     followed
    -0.67
    swer
    -0.66
    enough
    -0.65
    ortium
    -0.65
    uria
    -0.64
    cipl
    -0.62
    inence
    -0.61
    POSITIVE LOGITS
     outset
    1.83
     standpoint
    1.62
     perspective
    1.38
     vantage
    1.28
     sidelines
    1.27
     depths
    1.21
     viewpoint
    1.16
     beginning
    1.15
     ashes
    1.06
     mouths
    1.05
    Activations Density 0.148%

    No Known Activations