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. 8-RES-JB
    6. 3757
    Prev
    Next
    INDEX
    Explanations

    data related to technology specifications

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ange
    -0.79
     Zeit
    -0.77
     Jelly
    -0.75
     Freak
    -0.75
     Amer
    -0.74
     Wem
    -0.71
     Yo
    -0.71
    bush
    -0.70
     Christ
    -0.70
     Ezek
    -0.68
    POSITIVE LOGITS
    300
    1.21
    200
    1.18
    260
    1.17
    144
    1.17
    185
    1.17
    240
    1.15
    192
    1.15
    199
    1.14
    168
    1.13
    250
    1.13
    Activations Density 0.164%

    No Known Activations