INDEX

Explanations

cities, names, and visual items

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of existence or being

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

è¦ļéĨĴ

-0.63

 docking

-0.59

recomm

-0.58

âĢ¢âĢ¢

-0.58

 craving

-0.57

Ö¼

-0.56

fml

-0.56

 transporter

-0.56

 triangles

-0.55

tnc

-0.54

POSITIVE LOGITS

hett

0.81

chel

0.76

etooth

0.75

ocene

0.73

arios

0.73

emouth

0.73

asant

0.72

ppo

0.71

eps

0.70

nick

0.70

Activations Density 0.127%

cities, names, and visual items

words related to the concept of existence or being

No Comments

No Known Activations