Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 6772
    Prev
    Next
    INDEX
    Explanations

    action or movement-related verbs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "jump" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Smile
    -0.76
    zza
    -0.70
    minus
    -0.68
    been
    -0.65
    venge
    -0.65
    nda
    -0.64
    nce
    -0.62
     Ain
    -0.61
    matter
    -0.59
     waning
    -0.59
    POSITIVE LOGITS
    frog
    1.08
    start
    1.02
    started
    1.00
    starting
    0.88
     overboard
    0.86
     rope
    0.82
    lights
    0.81
    starter
    0.81
    fleet
    0.81
    uit
    0.81
    Activations Density 0.039%

    No Known Activations