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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11154
    Prev
    Next
    INDEX
    Explanations

    mentions of places, particularly emphasizing the word 'Ang'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Ang" in various contexts

    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
     externalToEVAOnly
    -0.80
    ÄŁ
    -0.76
    ãĥ¼ãĥ³
    -0.74
    cloth
    -0.71
    ords
    -0.63
    grades
    -0.63
    ño
    -0.63
     CTR
    -0.62
    ngth
    -0.61
     compensated
    -0.60
    POSITIVE LOGITS
    rily
    1.24
    uish
    1.14
    lia
    1.08
    lers
    0.96
    sty
    0.92
    emouth
    0.92
    ular
    0.86
    regor
    0.86
    strom
    0.83
    los
    0.82
    Activations Density 0.025%

    No Known Activations