© 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. 11-RES-JB
    11. 21865
    Prev
    Next
    INDEX
    Explanations

    words related to spiritual or metaphorical ascension (rising to a higher position or level)

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ascension or rising

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flan
    -0.65
     Grimes
    -0.65
     harder
    -0.64
    ãģ¦
    -0.63
    chy
    -0.63
     TIME
    -0.61
     Huck
    -0.60
     unfocusedRange
    -0.59
    zza
    -0.59
     Garr
    -0.58
    POSITIVE LOGITS
    ribed
    1.62
    ension
    1.55
    ribing
    1.50
    ribe
    1.46
    ribes
    1.37
    endant
    1.35
    ended
    1.28
    ensions
    1.27
    ript
    1.26
    endants
    1.19
    Activations Density 0.046%

    No Known Activations