© 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. 24363
    Prev
    Next
    INDEX
    Explanations

    phrases related to starting or initiating action towards a goal or task

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of moving forward or progressing with a task

    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
    merce
    -0.68
    ory
    -0.63
    ¶ħ
    -0.62
    orically
    -0.61
    iae
    -0.60
    resa
    -0.60
    ild
    -0.59
    ories
    -0.58
    cade
    -0.58
    Types
    -0.58
    POSITIVE LOGITS
     board
    1.14
     track
    1.09
    shore
    0.93
    screen
    0.93
    side
    0.91
     top
    0.90
    track
    0.89
    stage
    0.89
     topic
    0.86
    boarding
    0.85
    Activations Density 0.081%

    No Known Activations