© 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. 8717
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a return or comeback

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of "back" and related themes of return and verification

    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
    phant
    -0.90
    plane
    -0.87
    6
    -0.86
    665
    -0.82
    687
    -0.80
    463
    -0.80
    Area
    -0.79
    660
    -0.77
    365
    -0.77
     Ich
    -0.76
    POSITIVE LOGITS
    ¥ŀ
    0.92
    malink
    0.88
     Hind
    0.83
     backs
    0.78
     CrossRef
    0.77
     Hud
    0.77
     srf
    0.76
     Springer
    0.76
    displayText
    0.74
     Springs
    0.74
    Activations Density 0.338%

    No Known Activations