© 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. 2749
    Prev
    Next
    INDEX
    Explanations

    phrases related to continuity or duration

    oai_token-act-pair · gpt-3.5-turbo

    instances of 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 @ 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
    tle
    -0.73
     srfAttach
    -0.67
     Scientists
    -0.64
     Proxy
    -0.64
    TextColor
    -0.64
     professors
    -0.62
     Advantage
    -0.62
     ratified
    -0.61
     Picks
    -0.61
     substitutes
    -0.60
    POSITIVE LOGITS
     entirety
    0.99
     entire
    0.87
     aisle
    0.85
     region
    0.84
     process
    0.82
     country
    0.79
     remainder
    0.78
     halls
    0.77
     vicinity
    0.76
    town
    0.76
    Activations Density 0.067%

    No Known Activations