INDEX

Explanations

mentions of a specific brand or company

oai_token-act-pair · gpt-3.5-turbo

a range of emphatic, expressive language or emotional intensity

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 incent

-0.79

 encount

-0.78

 favoured

-0.76

 redes

-0.75

hement

-0.74

abwe

-0.74

 netted

-0.73

 abolished

-0.72

 lured

-0.71

 proport

-0.71

POSITIVE LOGITS

Reply

1.13

âĶĢâĶĢâĶĢâĶĢ

1.11

RAW

1.02

Anyway

0.99

Pause

0.97

Trivia

0.94

Advertisement

0.94

Narr

0.92

Anonymous

0.92

Write

0.91

Activations Density 0.458%

mentions of a specific brand or company

a range of emphatic, expressive language or emotional intensity

No Comments

No Known Activations