© 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. 8-RES-JB
    11. 7621
    Prev
    Next
    INDEX
    Explanations

    terms or phrases that are considered important or pertinent

    oai_token-act-pair · gpt-3.5-turbo

    the term "relevant" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rette
    -0.82
    jah
    -0.81
    iHUD
    -0.76
    hesda
    -0.74
    boats
    -0.71
    oise
    -0.71
    kay
    -0.71
    boat
    -0.71
    riage
    -0.69
    cker
    -0.69
    POSITIVE LOGITS
     footnote
    0.79
     newsp
    0.70
    ively
    0.68
     thereto
    0.68
    ioned
    0.67
     material
    0.67
     obser
    0.66
     contextual
    0.66
    arial
    0.66
    nces
    0.63
    Activations Density 0.032%

    No Known Activations