© 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. 11677
    Prev
    Next
    INDEX
    Explanations

    instances of the word "arrive" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "arrive" and its variations

    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
    SB
    -0.61
     independents
    -0.60
     regulating
    -0.59
     transparent
    -0.59
    ab
    -0.58
    MJ
    -0.58
     niche
    -0.58
     dumb
    -0.57
    af
    -0.57
     Nickel
    -0.55
    POSITIVE LOGITS
     arrive
    3.52
     arrives
    2.57
     arrived
    2.36
     arriving
    2.26
     arrival
    1.85
     arrivals
    1.51
     depart
    1.41
     disembark
    1.34
     Arri
    1.29
     converge
    1.27
    Activations Density 0.015%

    No Known Activations