INDEX

Explanations

phrases indicating time duration

oai_token-act-pair · gpt-3.5-turbo

references to governmental or organizational actions and decisions

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

.","

-0.72

 guiActiveUnfocused

-0.71

 cataly

-0.65

 underwater

-0.65

 ancestor

-0.63

 originate

-0.62

 stranded

-0.60

*/

-0.59

 otherwise

-0.59

"},"

-0.57

POSITIVE LOGITS

resa

0.92

notations

0.84

esty

0.83

 Conclusion

0.80

ibliography

0.77

laughter

0.74

itbart

0.73

swers

0.73

 irony

0.73

 rebutt

0.73

Activations Density 0.669%

phrases indicating time duration

references to governmental or organizational actions and decisions

No Comments

No Known Activations