© 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. 3110
    Prev
    Next
    INDEX
    Explanations

    memories or recollections

    oai_token-act-pair · gpt-3.5-turbo
    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
    tan
    -0.88
    oit
    -0.87
    ahime
    -0.79
    pex
    -0.75
    ÃŁ
    -0.74
    utenberg
    -0.74
    olitical
    -0.74
    ourage
    -0.72
    sonian
    -0.72
    otomy
    -0.72
    POSITIVE LOGITS
     vividly
    1.26
     remembering
    0.93
     memories
    0.92
     seeing
    0.90
     recalling
    0.90
     waking
    0.90
     hearing
    0.89
     vivid
    0.84
     fond
    0.83
     encountering
    0.83
    Activations Density 0.042%

    No Known Activations