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. 4861
    Prev
    Next
    INDEX
    Explanations

    mention of factors contributing to different situations

    oai_token-act-pair · gpt-3.5-turbo

    discussions about contributing factors to various situations or outcomes

    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
    ocry
    -0.79
    ebook
    -0.77
    ploma
    -0.77
    sterdam
    -0.76
     TAMADRA
    -0.75
    byter
    -0.75
    enda
    -0.75
    ACP
    -0.73
    rn
    -0.73
    iversary
    -0.72
    POSITIVE LOGITS
     factors
    1.44
     affecting
    1.15
     influencing
    1.12
     impacting
    1.10
     mitigating
    1.10
     determining
    1.09
     Factors
    1.08
     factor
    1.08
     influences
    1.08
     aggrav
    1.07
    Activations Density 0.457%

    No Known Activations