INDEX

Explanations

phrases recommending actions or products

oai_token-act-pair · gpt-3.5-turbo

phrases that express recommendations

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

brance

-0.72

aft

-0.64

bang

-0.62

 Hilbert

-0.62

inside

-0.62

hatt

-0.61

figure

-0.60

 hostage

-0.59

Bom

-0.59

behind

-0.58

POSITIVE LOGITS

Recommend

0.80

ournals

0.75

 recommending

0.73

recomm

0.69

iants

0.67

 scales

0.63

aring

0.63

 downloading

0.63

ered

0.63

ENDED

0.62

Activations Density 0.055%

phrases recommending actions or products

phrases that express recommendations

No Comments

No Known Activations