© 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. 16408
    Prev
    Next
    INDEX
    Explanations

    the word "actual"

    oai_token-act-pair · gpt-3.5-turbo

    the word "actual" and its variations in various contexts

    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
    wich
    -0.93
     ashore
    -0.78
    lain
    -0.72
    nan
    -0.70
    PAC
    -0.68
     Parad
    -0.67
    VC
    -0.66
    beam
    -0.65
    Bay
    -0.65
    greg
    -0.64
    POSITIVE LOGITS
    ignment
    0.87
     actual
    0.78
    isation
    0.77
    THING
    0.76
     malice
    0.75
    ité
    0.74
     truth
    0.73
    heastern
    0.73
    ITY
    0.73
    quickShipAvailable
    0.73
    Activations Density 0.008%

    No Known Activations