INDEX

Explanations

situations related to self-reflection and personal development

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

 glac

-0.66

 padd

-0.65

 respectively

-0.64

ws

-0.63

pri

-0.62

etimes

-0.62

wagen

-0.61

 indist

-0.61

 effected

-0.60

 agre

-0.58

POSITIVE LOGITS

 Explicit

0.94

 Conclusion

0.92

 SHARES

0.92

NCT

0.82

Ability

0.77

 Clean

0.76

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

0.74

 CONTIN

0.73

________________

0.71

maxwell

0.71

Activations Density 1.342%

situations related to self-reflection and personal development

No Comments

No Known Activations