© 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
    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. 12875
    Prev
    Next
    INDEX
    Explanations

    words related to competitiveness and competition

    oai_token-act-pair · gpt-3.5-turbo

    references to competitive environments and competitive factors

    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
    uras
    -0.77
    AMI
    -0.77
    ocument
    -0.74
    DonaldTrump
    -0.71
    ################
    -0.70
    hung
    -0.70
    slave
    -0.69
    gur
    -0.68
    aida
    -0.66
    istor
    -0.66
    POSITIVE LOGITS
    ly
    1.09
     advantage
    1.06
     disadvantage
    1.02
     Advantage
    0.96
     advantages
    0.94
     edge
    0.89
     bidding
    0.83
     disadvantages
    0.80
    daq
    0.80
     juices
    0.80
    Activations Density 0.025%

    No Known Activations