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. 5446
    Prev
    Next
    INDEX
    Explanations

    adjectives describing things in a specific manner

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating types or characteristics of things

    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
    idelines
    -0.78
    ĸļ
    -0.76
    alf
    -0.74
     CrossRef
    -0.74
     Below
    -0.71
    esses
    -0.70
     Beet
    -0.69
    çīĪ
    -0.68
    dn
    -0.68
    heid
    -0.67
    POSITIVE LOGITS
     thing
    1.32
     stuff
    0.92
     nonsense
    0.84
     crap
    0.84
     mentality
    0.84
     scenario
    0.83
     luck
    0.83
     behavior
    0.82
     guy
    0.82
     trauma
    0.82
    Activations Density 0.051%

    No Known Activations