INDEX

Explanations

dates or time periods

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a time frame, specifically the term "mid" followed by years

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

AVG

-0.79

 Cosponsors

-0.75

 DRAG

-0.68

ADRA

-0.65

 Painter

-0.63

 badges

-0.62

 Illum

-0.62

 Starr

-0.62

SOS

-0.62

 Neville

-0.61

POSITIVE LOGITS

season

1.07

sized

1.04

sent

1.03

term

1.02

range

1.01

round

1.01

century

1.00

distance

0.99

level

0.98

budget

0.98

Activations Density 0.025%

dates or time periods

phrases indicating a time frame, specifically the term "mid" followed by years

No Comments

No Known Activations