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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 10-RES-JB
    6. 20095
    Prev
    Next
    INDEX
    Explanations

    words related to changes, developments, and shifts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant changes or shifts in political and societal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tickets
    -0.91
     Tickets
    -0.86
    iddles
    -0.81
     fared
    -0.76
    mates
    -0.74
    bugs
    -0.72
    parts
    -0.71
     tickets
    -0.71
    eworks
    -0.71
    kids
    -0.70
    POSITIVE LOGITS
     willingness
    1.58
     tendency
    1.55
     realization
    1.50
     resurgence
    1.44
     reliance
    1.43
     insistence
    1.43
     emergence
    1.41
     reluctance
    1.40
     unwillingness
    1.38
     emphasis
    1.34
    Activations Density 0.394%

    No Known Activations