© 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. 1-RES-JB
    11. 2733
    Prev
    Next
    INDEX
    Explanations

    words related to communication or connection between different entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aft
    -0.84
    prus
    -0.78
    zn
    -0.78
    cott
    -0.77
    cise
    -0.74
    haps
    -0.73
    enic
    -0.73
    GE
    -0.71
    asper
    -0.68
    ihil
    -0.67
    POSITIVE LOGITS
     interactions
    1.38
     interaction
    1.25
     interacted
    0.90
     interacts
    0.88
     interact
    0.83
     interacting
    0.82
     experien
    0.81
    ivity
    0.81
     encounters
    0.80
    iquette
    0.79
    Activations Density 0.008%

    No Known Activations