© 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. 13949
    Prev
    Next
    INDEX
    Explanations

    instances of the word "goal"

    oai_token-act-pair · gpt-3.5-turbo

    statements or phrases related to objectives and aspirations

    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
     fluids
    -0.68
     jaws
    -0.66
     Geological
    -0.64
     Hath
    -0.63
    walking
    -0.63
     legends
    -0.61
    Versions
    -0.61
    Edited
    -0.61
    --------------------------------------------------------
    -0.61
    oute
    -0.60
    POSITIVE LOGITS
     goal
    1.06
    Goal
    1.06
    goal
    1.05
     Goal
    1.00
    posts
    0.95
     kicker
    0.84
    iture
    0.81
    oldemort
    0.78
    irement
    0.77
     goals
    0.77
    Activations Density 0.020%

    No Known Activations