© 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. 20093
    Prev
    Next
    INDEX
    Explanations

    instances of the word "come" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "come."

    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
    ricular
    -0.89
    icon
    -0.86
    apo
    -0.86
    inguished
    -0.85
    activ
    -0.85
    ²¾
    -0.85
    lav
    -0.84
    orthodox
    -0.82
    raid
    -0.81
    illusion
    -0.81
    POSITIVE LOGITS
     undone
    1.05
     WRITE
    0.90
     OUT
    0.75
     out
    0.75
     Steele
    0.74
     forth
    0.74
     Edison
    0.74
     pouring
    0.74
     Ley
    0.72
     Calais
    0.71
    Activations Density 0.041%

    No Known Activations