INDEX

Explanations

names and surnames, potentially from various contexts

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 gram

-0.61

 independ

-0.60

 invention

-0.58

 daytime

-0.55

iliation

-0.54

 distance

-0.54

 novelty

-0.54

 tabs

-0.53

 object

-0.53

NPC

-0.53

POSITIVE LOGITS

Ã±o

1.05

heimer

1.03

kamp

0.99

bilt

0.97

tsky

0.94

uthor

0.93

gaard

0.91

haar

0.91

hoff

0.91

baum

0.90

Activations Density 0.308%

names and surnames, potentially from various contexts

proper nouns, particularly names and places

No Comments

No Known Activations