INDEX

Explanations

phrases related to political figures and actions

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

 Schiff

-0.67

math

-0.65

 Majority

-0.63

geries

-0.61

 spoilers

-0.59

 Berman

-0.59

 Barron

-0.58

inks

-0.58

 srfAttach

-0.58

 Vaughn

-0.58

POSITIVE LOGITS

 encountered

1.06

 encount

0.96

 encounter

0.95

've

0.94

 deems

0.93

 deem

0.84

 frequ

0.83

 inherited

0.81

 undertook

0.79

 dreamed

0.79

Activations Density 0.681%

phrases related to political figures and actions

No Comments

No Known Activations