INDEX

Explanations

mentions of armed actions or conflicts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "armed."

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

rx

-0.97

rb

-0.77

HUD

-0.76

arget

-0.75

 Remastered

-0.72

article

-0.70

 Woodward

-0.69

 coli

-0.68

apest

-0.67

MQ

-0.67

POSITIVE LOGITS

 robbery

1.07

 armed

0.92

 guards

0.91

 insurrection

0.91

ament

0.90

 robberies

0.86

 robber

0.84

 robbers

0.84

 coup

0.80

 uprising

0.79

Activations Density 0.018%

mentions of armed actions or conflicts

instances of the word "armed."

No Comments

No Known Activations