© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 10959
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the end of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "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 @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.92
    PDATE
    -0.74
    esome
    -0.70
    kaya
    -0.68
    æ©Ł
    -0.67
    hips
    -0.66
    RNA
    -0.64
    chy
    -0.64
    kson
    -0.63
    IGHTS
    -0.60
    POSITIVE LOGITS
    angering
    1.28
    angered
    1.21
    ocrin
    1.20
    owment
    1.18
    ocrine
    1.12
    urance
    1.12
    orph
    1.07
    angers
    1.00
    points
    0.93
    ogenous
    0.91
    Activations Density 0.038%

    No Known Activations