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. 6-RES-JB
    6. 13032
    Prev
    Next
    INDEX
    Explanations

    phrases related to the transfer, movement, or relocation of people, information, or resources

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the act of moving or changing location of things, especially in the context of data, rights, or responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spot
    -0.75
    ace
    -0.73
    mouth
    -0.67
    76561
    -0.66
    deen
    -0.66
    Condition
    -0.64
    tips
    -0.64
    corn
    -0.63
    mil
    -0.62
    makers
    -0.62
    POSITIVE LOGITS
     seamlessly
    0.91
     away
    0.84
     into
    0.80
     gears
    0.79
    itably
    0.75
     onto
    0.74
     INTO
    0.72
     Away
    0.69
     alleg
    0.67
     toward
    0.67
    Activations Density 0.141%

    No Known Activations