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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 7789
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking extensive actions or measures

    oai_token-act-pair · gpt-3.5-turbo

    expressions of determination or effort in achieving goals

    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
    edIn
    -0.67
    elist
    -0.67
    ales
    -0.62
    itialized
    -0.55
    EE
    -0.55
     aging
    -0.55
     plur
    -0.55
    epad
    -0.55
    otive
    -0.54
     stagnant
    -0.53
    POSITIVE LOGITS
     possible
    1.09
     imaginable
    1.05
     practicable
    1.01
     conceivable
    0.99
     Possible
    0.97
    necessary
    0.96
     feasible
    0.91
     necessary
    0.80
    available
    0.75
     available
    0.70
    Activations Density 0.089%

    No Known Activations