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. 19943
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the current situation or status of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating existence or presence

    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
     ceremon
    -0.74
     senses
    -0.69
     Yor
    -0.68
    ishers
    -0.67
     canoe
    -0.67
    isher
    -0.67
     whistle
    -0.66
    haw
    -0.66
     Gain
    -0.66
    agues
    -0.64
    POSITIVE LOGITS
    KER
    0.83
    GRE
    0.78
    Reviewer
    0.74
     Solitaire
    0.73
    Chicken
    0.70
    LG
    0.70
    SU
    0.69
    Ĥİ
    0.68
     actually
    0.68
    VALUE
    0.67
    Activations Density 0.166%

    No Known Activations