© 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. 2001
    Prev
    Next
    INDEX
    Explanations

    phrases expressing that something is just the beginning or a small part of a larger issue or situation

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "icebergs" as a metaphor for underlying complexities

    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
    owship
    -1.00
    mson
    -0.86
    Merit
    -0.85
    ials
    -0.85
    ouver
    -0.83
    ailability
    -0.76
    ãĤ¹ãĥĪ
    -0.73
    mberg
    -0.71
    EMENT
    -0.69
    FACE
    -0.69
    POSITIVE LOGITS
     iceberg
    1.21
     toes
    0.84
    yip
    0.80
     scales
    0.78
    Tip
    0.70
     finger
    0.69
     needles
    0.66
     toe
    0.64
    ariat
    0.64
     tentacles
    0.63
    Activations Density 0.107%

    No Known Activations