INDEX

Explanations

descriptions related to products and movements

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

 clipboard

-0.66

 Gleaming

-0.59

 Jinn

-0.58

xit

-0.58

 Palest

-0.58

 Wonderland

-0.57

 Behavior

-0.56

 Keller

-0.55

«ĺ

-0.55

matically

-0.54

POSITIVE LOGITS

(>

1.24

ensity

0.76

atoes

0.75

iameter

0.73

(<

0.72

 stature

0.70

occup

0.65

(~

0.65

 expans

0.65

obl

0.64

Activations Density 2.541%

descriptions related to products and movements

No Comments

No Known Activations