© 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. 4-RES-JB
    11. 17172
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific acronym or company name 'AW'

    oai_token-act-pair · gpt-3.5-turbo

    references to "AW" which indicates a focus on specific code or tool names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vie
    -0.84
    ogue
    -0.76
     Townsend
    -0.69
     psy
    -0.68
    stros
    -0.67
    ozo
    -0.66
    istically
    -0.65
    orescent
    -0.64
    beam
    -0.63
    opol
    -0.63
    POSITIVE LOGITS
    ARDS
    1.25
    ARD
    1.06
    AW
    1.01
    AY
    0.98
    OND
    0.97
    IELD
    0.97
    IRED
    0.92
    ELL
    0.90
    ILA
    0.89
    akening
    0.88
    Activations Density 0.010%

    No Known Activations