INDEX

Explanations

references to conflict or war

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ocre

-0.84

aminer

-0.78

ocr

-0.74

icles

-0.72

ogene

-0.70

URES

-0.69

ħĭ

-0.67

ibilities

-0.66

 suspic

-0.66

OGR

-0.66

POSITIVE LOGITS

rior

1.33

riors

1.20

fare

1.17

lord

0.85

hammer

0.85

bler

0.84

lock

0.82

ner

0.81

ashtra

0.81

ring

0.80

Activations Density 0.006%

references to conflict or war

No Comments

No Known Activations