© 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. 8-RES-JB
    11. 17582
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of "end" or completion within a context

    oai_token-act-pair · gpt-3.5-turbo

    references to "end" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BLIC
    -0.72
    æ©Ł
    -0.69
    Interested
    -0.62
     suscept
    -0.61
     Dou
    -0.60
     acidic
    -0.58
    issance
    -0.58
     unusual
    -0.58
     Bastard
    -0.56
     irregular
    -0.55
    POSITIVE LOGITS
    owment
    1.47
    angering
    1.35
    angers
    1.17
    ocrine
    1.17
    ocrin
    1.16
    angered
    1.15
    urance
    1.07
    game
    1.06
    orph
    1.06
    points
    1.02
    Activations Density 0.062%

    No Known Activations