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. 4-RES-JB
    6. 17561
    Prev
    Next
    INDEX
    Explanations

    financial terms and company names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Nas" and related terms

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

    No Comments

    Negative Logits
    ffee
    -0.66
     damned
    -0.66
     ransom
    -0.64
    éģ
    -0.62
    OTT
    -0.62
    ODUCT
    -0.62
    IENCE
    -0.62
    fare
    -0.61
    å§
    -0.61
    BILITY
    -0.61
    POSITIVE LOGITS
    daq
    1.84
    rils
    1.11
    ilon
    1.05
    uit
    0.98
    emonic
    0.93
    apon
    0.93
     Nas
    0.88
    asa
    0.87
    DAQ
    0.86
    ule
    0.84
    Activations Density 0.008%

    No Known Activations