INDEX

Explanations

mentions of the name "Robin."

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

mble

-0.87

resso

-0.83

xual

-0.77

ormons

-0.75

chnology

-0.72

pora

-0.72

aeda

-0.71

ormon

-0.70

ĵĺ

-0.66

definition

-0.66

POSITIVE LOGITS

 Hood

1.30

ette

1.02

 Williams

0.90

alties

0.85

 Hanson

0.84

istics

0.81

aldo

0.81

Hob

0.78

ettes

0.77

hood

0.74

Activations Density 0.004%

mentions of the name "Robin."

No Comments

No Known Activations