© 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. 9-RES-JB
    11. 10109
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating movement or direction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "past" and its variations in the context of movement or interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¦ãĤ¹
    -0.75
    Introduced
    -0.74
    ickr
    -0.72
    mone
    -0.72
     nutshell
    -0.72
    azeera
    -0.71
    aspers
    -0.67
    DNA
    -0.67
    DN
    -0.67
    PDF
    -0.67
    POSITIVE LOGITS
     hills
    0.89
     parked
    0.86
     nearer
    0.86
     cliffs
    0.85
     bushes
    0.85
     midnight
    0.84
     him
    0.82
     shore
    0.82
     overhead
    0.81
     midfield
    0.80
    Activations Density 0.188%

    No Known Activations