Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 17437
    Prev
    Next
    INDEX
    Explanations

    specific instances of financial years (FY) and the verb "cater"

    oai_token-act-pair · gpt-3.5-turbo

    references to fiscal years and related budgetary terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scotia
    -0.80
     Roses
    -0.69
    Diamond
    -0.69
    ial
    -0.68
    ials
    -0.68
     Ic
    -0.65
    enberg
    -0.65
     "$:/
    -0.64
     Tunnel
    -0.64
    士
    -0.63
    POSITIVE LOGITS
    pillar
    0.94
    reen
    0.87
    pheus
    0.84
    ramid
    0.83
    alez
    0.82
    phis
    0.76
    urate
    0.75
    GAN
    0.75
    anical
    0.74
    ¦
    0.73
    Activations Density 0.083%

    No Known Activations