INDEX

Explanations

phrases related to specific technical instructions

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

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

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ò

-0.79

hur

-0.73

ghan

-0.72

quet

-0.72

uel

-0.70

urous

-0.70

tein

-0.69

NF

-0.68

riers

-0.66

fle

-0.65

POSITIVE LOGITS

atics

1.05

atically

1.02

wide

0.98

atic

0.95

ctl

0.92

 tray

0.82

ycle

0.82

 administrator

0.79

 integ

0.78

arily

0.75

Activations Density 0.029%

phrases related to specific technical instructions

No Comments

No Known Activations