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. 9-RES-JB
    6. 12978
    Prev
    Next
    INDEX
    Explanations

    reflections or thoughts about personal experiences and observations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal thoughts and realizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vale
    -0.71
     yourselves
    -0.67
    ittees
    -0.67
    reb
    -0.62
     Pearce
    -0.60
     prefers
    -0.60
    adra
    -0.59
     Slovakia
    -0.59
    visory
    -0.58
    ospons
    -0.57
    POSITIVE LOGITS
     enorm
    0.86
     somehow
    0.84
     Suddenly
    0.83
    Suddenly
    0.79
    Something
    0.78
     absurdity
    0.77
    Damn
    0.76
     maybe
    0.76
    Maybe
    0.75
    maybe
    0.72
    Activations Density 0.421%

    No Known Activations