© 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. 10-RES-JB
    11. 21344
    Prev
    Next
    INDEX
    Explanations

    words related to events or actions in history

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and the word "and" indicating connections between various actions and events

    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
    weak
    -0.76
    acceptable
    -0.72
    diff
    -0.70
    ieth
    -0.68
    gest
    -0.67
    NULL
    -0.66
    antz
    -0.63
    ibble
    -0.63
    >[
    -0.62
    ivot
    -0.62
    POSITIVE LOGITS
     proceeded
    1.36
     began
    1.32
     became
    1.25
     promptly
    1.25
     subsequently
    1.22
     eventually
    1.21
     commenced
    1.21
     consequently
    1.13
     thereafter
    1.11
     undertook
    1.10
    Activations Density 0.260%

    No Known Activations