© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 17244
    Prev
    Next
    INDEX
    Explanations

    the word "second" used in a context indicating ranking or importance

    oai_token-act-pair · gpt-3.5-turbo

    references to rankings or positions characterized as "second" or "third."

    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
    Rules
    -0.66
    XY
    -0.66
    ihil
    -0.65
    IRC
    -0.64
    ãĤĭ
    -0.63
    Adams
    -0.62
    Marginal
    -0.62
    Paper
    -0.61
    tics
    -0.61
    agons
    -0.61
    POSITIVE LOGITS
     baseman
    1.18
    arily
    1.15
    hand
    1.13
    isl
    0.80
    aries
    0.80
     cousin
    0.77
     consecutive
    0.75
     successive
    0.74
     responders
    0.72
    uces
    0.71
    Activations Density 0.057%

    No Known Activations