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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7288
    Prev
    Next
    INDEX
    Explanations

    phrases related to an action being influenced or impacted by various factors

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "by" used in various contexts related to obstacles or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LO
    -0.76
    ettle
    -0.72
    thal
    -0.71
    LS
    -0.70
    llor
    -0.69
    apest
    -0.69
    bay
    -0.69
    WA
    -0.68
    asy
    -0.67
    iate
    -0.67
    POSITIVE LOGITS
     virtue
    1.22
    products
    0.93
     fiat
    0.85
    laws
    0.83
     sheer
    0.79
     successive
    0.71
     necessity
    0.70
     gravity
    0.70
     multiplying
    0.69
     leaps
    0.69
    Activations Density 0.133%

    No Known Activations