INDEX

Explanations

adjectives describing low or negative qualities

oai_token-act-pair · gpt-3.5-turbo

negative descriptors related to quality or performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

leans

-0.84

ju

-0.73

plane

-0.72

frey

-0.72

llers

-0.70

cise

-0.70

cript

-0.70

planes

-0.68

alde

-0.68

lean

-0.67

POSITIVE LOGITS

glers

0.88

 miser

0.88

luster

0.80

 Downs

0.75

 rollout

0.68

 incompet

0.68

 excuses

0.68

nesses

0.68

 incompetence

0.68

 Spac

0.66

Activations Density 0.085%

adjectives describing low or negative qualities

negative descriptors related to quality or performance

No Comments

No Known Activations