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. 18931
    Prev
    Next
    INDEX
    Explanations

    years and dates, as well as the launch or founding events of various entities or organizations

    oai_token-act-pair · gpt-3.5-turbo

    dates and years associated with significant events or milestones

    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
    idia
    -0.69
    chance
    -0.68
    hide
    -0.66
    natureconservancy
    -0.66
     undecided
    -0.65
    imi
    -0.64
     faint
    -0.64
    dain
    -0.63
    ides
    -0.63
    rared
    -0.62
    POSITIVE LOGITS
     consisted
    1.00
    sequently
    0.86
     rebuilt
    0.85
     operated
    0.83
     renamed
    0.81
     followed
    0.81
     lasted
    0.81
     thereafter
    0.80
     restruct
    0.79
     comprised
    0.79
    Activations Density 0.567%

    No Known Activations