© 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 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. 3421
    Prev
    Next
    INDEX
    Explanations

    terms related to geological or scientific concepts

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to tectonic activities and geological processes

    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
    PDATE
    -0.79
    LOAD
    -0.70
    FTWARE
    -0.64
    Bloomberg
    -0.63
     exha
    -0.62
    CHR
    -0.56
    gain
    -0.55
    ãĥ£
    -0.55
     Leopard
    -0.55
    ¯¯¯¯
    -0.54
    POSITIVE LOGITS
    icut
    1.26
    oral
    1.19
    onics
    1.16
    ors
    1.12
    ions
    1.02
    ures
    1.01
    eering
    0.93
    ively
    0.93
    igent
    0.92
    ional
    0.92
    Activations Density 0.036%

    No Known Activations