© 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. 3326
    Prev
    Next
    INDEX
    Explanations

    the word "comes" followed by different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "when it comes" and its variations

    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
    -1.02
    icon
    -0.95
    apixel
    -0.87
    orthodox
    -0.82
    icons
    -0.80
    sav
    -0.78
    illusion
    -0.78
    bush
    -0.78
    raid
    -0.77
    olor
    -0.77
    POSITIVE LOGITS
     undone
    0.98
     WRITE
    0.83
     Steele
    0.81
     Nieto
    0.77
     Maduro
    0.74
     OUT
    0.73
     Maz
    0.71
     forward
    0.71
     forth
    0.70
     Gerrard
    0.70
    Activations Density 0.025%

    No Known Activations