© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 12250
    Prev
    Next
    INDEX
    Explanations

    phrases related to forest destruction in the Amazon rainforest

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" and other related definite articles

    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
    ason
    -0.73
    utan
    -0.71
    edit
    -0.71
    iji
    -0.68
    âĢł
    -0.67
    thood
    -0.66
    aken
    -0.66
    nesty
    -0.65
    ade
    -0.65
    perse
    -0.64
    POSITIVE LOGITS
     slightest
    1.18
     smallest
    1.06
     weakest
    1.03
    oret
    1.01
     entirety
    1.00
     biggest
    0.99
    ses
    0.99
     hardest
    0.98
     whole
    0.97
     entire
    0.97
    Activations Density 0.462%

    No Known Activations