© 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. 3-RES-JB
    11. 15230
    Prev
    Next
    INDEX
    Explanations

    the name "Melissa" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Melissa."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.92
    stroke
    -0.84
    uned
    -0.78
    culosis
    -0.77
    redo
    -0.77
    amins
    -0.73
    ãĤĮ
    -0.73
    ition
    -0.71
    arist
    -0.71
    yrinth
    -0.71
    POSITIVE LOGITS
    issa
    0.88
     ILCS
    0.82
     Melissa
    0.79
     Foods
    0.68
     Matthews
    0.67
     Ether
    0.67
     Tome
    0.65
     Brach
    0.65
     McCarthy
    0.65
     Levant
    0.64
    Activations Density 0.014%

    No Known Activations