INDEX

Explanations

adjectives expressing positive feelings or qualities

oai_token-act-pair · gpt-3.5-turbo

strong affirmative actions or characteristics related to emotional or social contexts

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

 chronological

-0.64

 Metatron

-0.61

BuyableInstoreAndOnline

-0.59

maxwell

-0.58

 manag

-0.58

 compliance

-0.56

 Miko

-0.56

rade

-0.55

 lineback

-0.55

KGB

-0.54

POSITIVE LOGITS

ãĥ¼ãĤ¯

0.81

abouts

0.79

itud

0.76

eming

0.72

hett

0.67

na

0.65

nda

0.63

burgh

0.63

glas

0.63

 Alam

0.63

Activations Density 0.400%

adjectives expressing positive feelings or qualities

strong affirmative actions or characteristics related to emotional or social contexts

No Comments

No Known Activations