INDEX

Explanations

phrases encouraging or discouraging specific behaviors

oai_token-act-pair · gpt-3.5-turbo

phrases that encourage positive behaviors and attitudes

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

PsyNetMessage

-0.63

 Explosion

-0.62

 Prescott

-0.62

 Lines

-0.61

 suffice

-0.60

 reconstruction

-0.60

 Topics

-0.60

 Strait

-0.59

 autopsy

-0.59

 fray

-0.59

POSITIVE LOGITS

 able

1.14

 thankful

1.13

 aware

1.09

 afraid

1.02

 honest

1.01

 grateful

1.01

 careful

1.01

friends

0.96

 ashamed

0.96

 proud

0.95

Activations Density 0.167%

phrases encouraging or discouraging specific behaviors

phrases that encourage positive behaviors and attitudes

No Comments

No Known Activations