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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-RES-JB
    6. 6923
    Prev
    Next
    INDEX
    Explanations

    phrases related to motivation or driving forward a cause

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of the word "push" and its derivatives, indicating a focus on the act of advocating or moving something forward

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oxide
    -0.75
    ateur
    -0.75
    eye
    -0.74
    mint
    -0.74
    psons
    -0.73
    enfranch
    -0.67
    venge
    -0.67
    cin
    -0.65
    Condition
    -0.65
    weather
    -0.65
    POSITIVE LOGITS
     forward
    1.30
     boundaries
    1.24
     ahead
    1.20
     buttons
    1.19
     onward
    1.15
     aside
    1.12
     harder
    1.07
     forwards
    1.01
     toward
    0.99
     envelope
    0.98
    Activations Density 0.101%

    No Known Activations