© 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. 11291
    Prev
    Next
    INDEX
    Explanations

    instances of the word "intended" in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express purpose or intent

    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
    SPONSORED
    -0.82
    upon
    -0.73
    oner
    -0.72
     Quan
    -0.71
    Du
    -0.65
    visor
    -0.65
    stood
    -0.64
    inas
    -0.63
    cit
    -0.62
    levels
    -0.62
    POSITIVE LOGITS
     intended
    1.10
     intending
    0.86
     Seym
    0.83
    ĸļ
    0.82
     referen
    0.80
     misunder
    0.79
    ividual
    0.79
     meant
    0.79
     Palestin
    0.78
     practition
    0.77
    Activations Density 0.009%

    No Known Activations