© 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. 3-RES-JB
    11. 10711
    Prev
    Next
    INDEX
    Explanations

    words related to venturing out or embarking on a new experience or endeavor

    oai_token-act-pair · gpt-3.5-turbo

    references to social events or outings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    organic
    -0.77
    akia
    -0.75
    paying
    -0.75
    tymology
    -0.73
    reme
    -0.73
    otype
    -0.72
    uchs
    -0.71
    grave
    -0.71
    poral
    -0.69
    iggs
    -0.68
    POSITIVE LOGITS
    GGGGGGGG
    0.84
    spection
    0.80
     outing
    0.78
     Neptune
    0.76
    iannopoulos
    0.73
    ãĥĩ
    0.72
     Trip
    0.69
     APR
    0.68
     Tanz
    0.68
    yssey
    0.66
    Activations Density 0.019%

    No Known Activations