INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ERA

-0.84

================================================================

-0.83

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.83

é»Ĵ

-0.82

ODUCT

-0.80

åŃ

-0.74

ãĥ¼ãĥĨãĤ£

-0.73

 Colossus

-0.71

EngineDebug

-0.68

Progress

-0.67

POSITIVE LOGITS

Naj

0.96

wcs

0.90

akh

0.89

ees

0.87

ee

0.86

merga

0.84

daq

0.83

jar

0.83

eb

0.82

odies

0.82

Activations Density 0.014%

names of individuals

proper nouns, specifically names and places

No Comments

No Known Activations