INDEX

Explanations

phrases related to a specific style or manner, particularly one associated with strong or forceful action

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

atoon

-0.90

ora

-0.86

arte

-0.83

arus

-0.80

ma

-0.79

liga

-0.78

leased

-0.76

wright

-0.75

ajor

-0.75

ificant

-0.74

POSITIVE LOGITS

 burial

0.82

 immersion

0.80

 refinement

0.79

 confinement

0.74

 executions

0.74

 coffin

0.73

 clothing

0.72

 garbage

0.70

 mockery

0.70

 attire

0.69

Activations Density 0.029%

phrases related to a specific style or manner, particularly one associated with strong or forceful action

No Comments

No Known Activations