INDEX

Explanations

organizations or entities and their relationships with specific activities or qualities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating organizational or functional support

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.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

pool

-0.81

pite

-0.77

DK

-0.75

fw

-0.74

hy

-0.71

henko

-0.71

 Conclusion

-0.66

/+

-0.66

case

-0.64

RN

-0.63

POSITIVE LOGITS

 laun

0.84

 famed

0.80

 pione

0.80

Þ

0.75

 acronym

0.73

 acron

0.72

 disgr

0.72

Â¯Â¯Â¯Â¯

0.71

 fame

0.70

ò

0.70

Activations Density 0.264%

organizations or entities and their relationships with specific activities or qualities

phrases indicating organizational or functional support

No Comments

No Known Activations