© 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. 2070
    Prev
    Next
    INDEX
    Explanations

    the word "single"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "single."

    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
    Downloadha
    -0.91
     Bulg
    -0.81
    ITNESS
    -0.76
     Hoo
    -0.71
    姫
    -0.68
    arium
    -0.65
     Sweeney
    -0.65
     Norton
    -0.64
    omo
    -0.63
     Bog
    -0.63
    POSITIVE LOGITS
    handedly
    1.27
     single
    0.88
    mitting
    0.81
    single
    0.80
    player
    0.79
    ton
    0.77
    plex
    0.76
     digit
    0.74
    heartedly
    0.71
    secut
    0.70
    Activations Density 0.017%

    No Known Activations