INDEX

Explanations

phrases related to appreciation and recognition

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

 inver

-0.70

waters

-0.69

itches

-0.65

 trash

-0.63

 pulp

-0.63

fuck

-0.63

Sty

-0.62

 mock

-0.62

USS

-0.61

 nude

-0.61

POSITIVE LOGITS

 bestowed

1.06

 afforded

0.87

 conferred

0.85

 arising

0.81

 accrued

0.78

 incurred

0.77

 levied

0.76

 Towards

0.76

 exerted

0.76

placed

0.75

Activations Density 2.279%

phrases related to appreciation and recognition

No Comments

No Known Activations