INDEX

Explanations

phrases indicating temporal references or changes related to events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

 Lastly

-0.86

)))

-0.81

"}],"

-0.78

"]

-0.77

"))

-0.77

))))

-0.77

DES

-0.75

Repeat

-0.73

"!

-0.72

trump

-0.72

POSITIVE LOGITS

 starters

0.72

 industrialized

0.69

sofar

0.65

 sooner

0.62

 polls

0.60

verning

0.60

 older

0.60

oret

0.59

 fewer

0.58

 longtime

0.58

Activations Density 0.456%

phrases indicating temporal references or changes related to events

No Comments

No Known Activations