© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 15799
    Prev
    Next
    INDEX
    Explanations

    terms related to implications or consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to consequences or effects of actions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abee
    -0.76
    jong
    -0.62
    erate
    -0.61
    %]
    -0.61
    unte
    -0.61
    chi
    -0.61
    berry
    -0.59
    walk
    -0.58
    eb
    -0.56
    Happy
    -0.56
    POSITIVE LOGITS
     implications
    3.62
     ramifications
    2.95
     repercussions
    2.34
     consequences
    2.24
     implication
    2.14
     significance
    1.65
     Impl
    1.58
     impacts
    1.50
     relevance
    1.47
     possibilities
    1.45
    Activations Density 0.013%

    No Known Activations