INDEX

Explanations

phrases related to economic events and financial matters, particularly involving numbers and statistics

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

umat

-0.78

ocrat

-0.76

fell

-0.76

ocument

-0.74

obook

-0.74

uma

-0.74

matter

-0.74

olla

-0.74

rio

-0.73

scribe

-0.73

POSITIVE LOGITS

 assorted

1.08

 willingness

1.06

 inability

1.01

 occasional

0.99

 lack

0.98

 penchant

0.97

 consequ

0.92

 unwillingness

0.91

 susceptibility

0.91

 adherence

0.91

Activations Density 2.345%

phrases related to economic events and financial matters, particularly involving numbers and statistics

No Comments

No Known Activations