INDEX

Explanations

proper names or surnames

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

iencies

-0.81

geries

-0.71

LEASE

-0.64

noon

-0.60

 impair

-0.56

 lockout

-0.56

ignt

-0.55

 accommodation

-0.55

undai

-0.55

 Binding

-0.55

POSITIVE LOGITS

 said

1.17

 replied

1.16

 joked

1.13

 exclaimed

1.08

 remarked

1.07

 told

1.05

 wrote

1.02

 says

1.02

 explained

1.00

 Says

0.93

Activations Density 0.176%

proper names or surnames

proper nouns, particularly names

No Comments

No Known Activations