INDEX

Explanations

topics related to economic research, specifically in the context of minimum wage studies and bias in evidence interpretation

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

pleted

-0.79

Delivery

-0.76

VIP

-0.74

Crew

-0.71

 downed

-0.71

 renovations

-0.70

 SOLD

-0.70

 Crush

-0.69

 Tonight

-0.66

ðŁĺ

-0.66

POSITIVE LOGITS

 empir

1.32

 methodological

1.27

 empirical

1.26

 rhetorical

1.25

 analytic

1.18

 philosoph

1.17

 conclusions

1.16

 cynicism

1.15

 epist

1.13

 causation

1.12

Activations Density 7.167%

topics related to economic research, specifically in the context of minimum wage studies and bias in evidence interpretation

No Comments

No Known Activations