INDEX

Explanations

phrases and words related to operations and logistics

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

ãĤ©

-0.77

arton

-0.75

hus

-0.73

aez

-0.70

udeau

-0.65

bitious

-0.65

sonian

-0.65

yi

-0.65

cil

-0.65

izont

-0.63

POSITIVE LOGITS

ally

0.94

eering

0.90

ional

0.89

ality

0.80

 tempo

0.78

 manuals

0.77

 undertaken

0.77

 conducted

0.76

ament

0.75

ername

0.74

Activations Density 0.032%

phrases and words related to operations and logistics

No Comments

No Known Activations