© 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. 0-RES-JB
    11. 4773
    Prev
    Next
    INDEX
    Explanations

    references to long-running series or activities

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "long-running" in relation to projects or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     letter
    -0.65
     reaff
    -0.64
     ent
    -0.64
     personalized
    -0.62
     shaped
    -0.60
     sign
    -0.59
    ×ķ
    -0.59
     plur
    -0.59
     plate
    -0.59
     lens
    -0.58
    POSITIVE LOGITS
    running
    4.14
    runners
    2.21
    runner
    2.12
    runs
    1.91
    Running
    1.80
    run
    1.67
     running
    1.51
     Running
    1.47
    walking
    1.40
    standing
    1.40
    Activations Density 0.011%

    No Known Activations