INDEX

Explanations

phrases indicating emphasis or importance

oai_token-act-pair · gpt-3.5-turbo

the repeated reference to a specific season in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ilitarian

-0.70

masters

-0.68

ickets

-0.65

aws

-0.64

oidal

-0.64

oller

-0.63

gans

-0.62

acers

-0.62

pots

-0.61

-0.60

POSITIVE LOGITS

 week

1.25

 year

1.08

 month

1.07

 morning

1.04

 afternoon

1.04

 semester

1.03

 weekend

1.00

 century

0.89

 evening

0.88

 summer

0.83

Activations Density 0.122%

phrases indicating emphasis or importance

the repeated reference to a specific season in various contexts

No Comments

No Known Activations