© 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. 4300
    Prev
    Next
    INDEX
    Explanations

    phrases related to military organizations and defense systems

    oai_token-act-pair · gpt-3.5-turbo

    references to political or military organizations and programs

    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
    76561
    -0.83
    ãĤ´ãĥ³
    -0.82
    leon
    -0.76
    matter
    -0.69
    abre
    -0.63
     miscar
    -0.62
    rue
    -0.62
    nect
    -0.62
    fly
    -0.60
    stros
    -0.59
    POSITIVE LOGITS
     (
    1.42
     ("
    1.32
     ('
    1.13
     (?,
    1.13
     ([
    1.07
     (*
    1.01
     (.
    1.00
     (&
    0.98
     [(
    0.97
     (=
    0.96
    Activations Density 0.545%

    No Known Activations