INDEX

Explanations

instances of the word "after" indicating a sequence of events or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

å¥³

-0.83

soDeliveryDate

-0.80

Anyway

-0.80

aez

-0.79

ichick

-0.75

ison

-0.75

eyes

-0.74

lems

-0.74

xxxx

-0.73

ethe

-0.72

POSITIVE LOGITS

 announcing

0.90

 discovering

0.90

noon

0.88

 losing

0.88

math

0.87

 failing

0.84

 enduring

0.84

 defeating

0.83

 disappointing

0.82

 Hurricane

0.82

Activations Density 0.068%

instances of the word "after" indicating a sequence of events or actions

No Comments

No Known Activations