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. 22061
    Prev
    Next
    INDEX
    Explanations

    technical terms or details within texts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to detailed explanations and foundational elements in a discussion

    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
    dinand
    -0.93
    heid
    -0.82
    rican
    -0.77
    ende
    -0.77
    ellow
    -0.74
    oho
    -0.73
    artney
    -0.72
    ega
    -0.72
    ove
    -0.71
    riched
    -0.71
    POSITIVE LOGITS
    iest
    0.96
     thereof
    0.96
     specifics
    0.93
     gist
    0.89
     details
    0.88
     fallacy
    0.84
     stuff
    0.82
     workings
    0.81
     factor
    0.81
     implications
    0.81
    Activations Density 0.285%

    No Known Activations