INDEX

Explanations

phrases describing incremental growth or escalation

oai_token-act-pair · gpt-3.5-turbo

numerical data and statistical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 lifes

-0.83

 reflex

-0.81

 instinct

-0.81

 shorthand

-0.78

 hero

-0.73

 sucker

-0.71

 furnace

-0.71

 raft

-0.70

 taste

-0.70

 commission

-0.69

POSITIVE LOGITS

Finally

1.80

Lastly

1.78

Conclusion

1.71

Regarding

1.60

Meanwhile

1.56

Overall

1.54

Another

1.53

Advertisements

1.50

Nevertheless

1.50

However

1.50

Activations Density 0.559%

phrases describing incremental growth or escalation

numerical data and statistical references

No Comments

No Known Activations