INDEX

Explanations

phrases indicating collective agreement or consensus based on evidence

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

ror

-0.76

osponsors

-0.71

advertisement

-0.65

itant

-0.65

AMA

-0.63

urg

-0.63

iqueness

-0.63

igmat

-0.61

ucha

-0.61

ira

-0.60

POSITIVE LOGITS

 onwards

1.24

 onward

1.02

 derived

0.81

 standpoint

0.78

 glean

0.78

 sprang

0.77

 flowed

0.77

 derives

0.75

 derive

0.75

 emerges

0.73

Activations Density 0.062%

phrases indicating collective agreement or consensus based on evidence

No Comments

No Known Activations