INDEX

Explanations

words related to fatal incidents or deaths

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

orthy

-0.82

arte

-0.78

 Remastered

-0.77

erous

-0.75

annis

-0.75

here

-0.74

rica

-0.74

berman

-0.73

MAS

-0.70

meric

-0.67

POSITIVE LOGITS

istic

1.13

istically

1.12

ities

1.10

 flaw

1.04

ized

1.01

 accidents

0.96

izing

0.94

 shootings

0.93

ist

0.92

 fatal

0.90

Activations Density 0.008%

words related to fatal incidents or deaths

No Comments

No Known Activations