© 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. 2-RES-JB
    11. 23250
    Prev
    Next
    INDEX
    Explanations

    instances where something or someone is actively involved in a specific event, activity, or program

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "participating" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iness
    -0.90
    pel
    -0.84
    cmp
    -0.81
    talk
    -0.79
    oot
    -0.79
    wn
    -0.78
    oho
    -0.77
    cms
    -0.77
    ung
    -0.76
    yon
    -0.74
    POSITIVE LOGITS
    redients
    0.77
     alcoholic
    0.75
     Pengu
    0.75
     mammalian
    0.74
     organisms
    0.74
     spheres
    0.73
    NESS
    0.73
     fractions
    0.72
     electron
    0.72
     rodents
    0.72
    Activations Density 0.124%

    No Known Activations