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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 10696
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations ending with "land"

    oai_token-act-pair · gpt-3.5-turbo

    words containing "land."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cumbers
    -0.91
    ¥ŀ
    -0.80
     tremend
    -0.78
     millenn
    -0.77
     eleph
    -0.70
     undermin
    -0.67
     periodic
    -0.66
    senal
    -0.65
    ollah
    -0.64
     corrective
    -0.64
    POSITIVE LOGITS
    scape
    1.06
    marks
    0.97
    ward
    0.93
    estine
    0.91
    gra
    0.89
    mark
    0.86
    lord
    0.85
    side
    0.84
    mass
    0.84
    lords
    0.81
    Activations Density 0.014%

    No Known Activations