INDEX

Explanations

positive outcomes of complex scenarios or 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_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

 acron

-0.63

 Hawks

-0.58

IRC

-0.57

saf

-0.57

 prosecut

-0.56

MSN

-0.56

ARCH

-0.55

ciplinary

-0.55

 Regulatory

-0.55

autions

-0.55

POSITIVE LOGITS

 rather

0.79

 instead

0.78

 while

0.76

 whereas

0.75

0.73

.[

0.71

rather

0.69

.''.

0.69

instead

0.69

 irrespective

0.68

Activations Density 0.472%

positive outcomes of complex scenarios or events

No Comments

No Known Activations