INDEX

Explanations

words associated with destruction or damage

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

eve

-0.89

birth

-0.78

ORGE

-0.78

women

-0.77

xon

-0.72

meal

-0.71

yip

-0.69

 Sakuya

-0.68

 hemor

-0.67

masters

-0.66

POSITIVE LOGITS

anca

1.46

eness

1.10

anches

0.92

anch

0.91

ahn

0.90

ack

0.88

anc

0.87

ossom

0.86

ilty

0.86

oks

0.85

Activations Density 0.004%

words associated with destruction or damage

No Comments

No Known Activations