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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-RES-JB
    6. 5854
    Prev
    Next
    INDEX
    Explanations

    organizations or individuals with specific names

    oai_token-act-pair · gpt-3.5-turbo

    commas and punctuation indicating lists or separations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irie
    -0.73
    sburg
    -0.72
    odes
    -0.69
    rast
    -0.65
    izen
    -0.65
    othe
    -0.64
    osexual
    -0.63
    ood
    -0.61
    sein
    -0.60
    uces
    -0.60
    POSITIVE LOGITS
     which
    1.21
     whose
    1.20
     aka
    1.06
    whose
    1.05
    which
    0.96
     although
    0.94
     who
    0.93
     whereas
    0.87
     namely
    0.84
    Magikarp
    0.83
    Activations Density 0.408%

    No Known Activations