INDEX

Explanations

specific references to locations or titles within sentences

oai_token-act-pair · gpt-3.5-turbo

phrases that involve specific articles and common nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ptions

-0.66

arians

-0.66

 wisely

-0.64

 accordingly

-0.64

coins

-0.63

 respectively

-0.62

cers

-0.62

agree

-0.62

checks

-0.61

wards

-0.61

POSITIVE LOGITS

 same

0.90

 Kremlin

0.79

 midst

0.78

 infamous

0.74

 slightest

0.74

 outskirts

0.73

 smallest

0.72

 upcoming

0.72

 opposite

0.69

same

0.69

Activations Density 0.400%

specific references to locations or titles within sentences

phrases that involve specific articles and common nouns

No Comments

No Known Activations