INDEX

Explanations

adjectives and phrases indicating emphasis or importance

oai_token-act-pair · gpt-3.5-turbo

specific terms and references associated with titles and articles

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

 trails

-0.80

 Cups

-0.78

 Bots

-0.77

Vert

-0.77

units

-0.73

 embassies

-0.73

models

-0.72

 Trails

-0.71

 tablets

-0.71

 ankles

-0.71

POSITIVE LOGITS

illary

0.84

 standpoint

0.82

achable

0.82

amic

0.74

estinal

0.74

chie

0.71

iece

0.71

ogram

0.71

ignant

0.70

able

0.68

Activations Density 0.317%

adjectives and phrases indicating emphasis or importance

specific terms and references associated with titles and articles

No Comments

No Known Activations