INDEX

Explanations

details related to specific events or historical facts

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

bold

-0.69

oner

-0.69

INC

-0.69

WER

-0.68

 Engineers

-0.64

must

-0.63

ternally

-0.62

ono

-0.61

beit

-0.60

 ASAP

-0.59

POSITIVE LOGITS

 confronted

0.85

 slightest

0.81

 arrives

0.78

 arrive

0.77

 approached

0.76

 pressed

0.75

 asked

0.74

 arrived

0.73

 finished

0.73

 finally

0.70

Activations Density 1.251%

details related to specific events or historical facts

No Comments

No Known Activations