INDEX

Explanations

references to military aircraft, specifically fighter jets

oai_token-act-pair · gpt-3.5-turbo

references to military aircraft and jets

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.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

 Cumber

-0.87

âĸ¬

-0.74

 Hallow

-0.71

 Birch

-0.70

ãĥ´

-0.68

 Alzheimer

-0.68

 Camden

-0.67

Honest

-0.66

 Territories

-0.64

 Fine

-0.63

POSITIVE LOGITS

 stationed

1.02

 patrolling

0.96

crew

0.95

 deployed

0.95

hops

0.94

 dispatched

0.91

linger

0.90

fighters

0.86

 squadron

0.86

piracy

0.86

Activations Density 0.052%

references to military aircraft, specifically fighter jets

references to military aircraft and jets

No Comments

No Known Activations