INDEX

Explanations

phrases related to technical terms or jargon used in discussions about software development and network upgrades

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.",

-0.78

.:

-0.76

%.

-0.69

reating

-0.67

cause

-0.66

unless

-0.64

":[

-0.64

!!!!!

-0.63

maxwell

-0.63

Medium

-0.63

POSITIVE LOGITS

*)

1.08

)]

1.00

})

0.94

)]

0.92

)}

0.91

?)

0.87

?)

0.81

)\

0.81

)|

0.79

+)

0.78

Activations Density 6.528%

phrases related to technical terms or jargon used in discussions about software development and network upgrades

No Comments

No Known Activations