INDEX

Explanations

the name "Anton" appearing in the text

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Anton."

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

glers

-0.94

lder

-0.76

eled

-0.76

ãĤĭ

-0.74

pees

-0.70

Kit

-0.70

FFER

-0.68

FU

-0.67

tc

-0.67

mable

-0.66

POSITIVE LOGITS

inian

1.11

aic

1.06

inus

1.03

 Anton

1.02

opoulos

0.98

iol

0.97

ique

0.91

illo

0.91

iques

0.91

ion

0.90

Activations Density 0.015%

the name "Anton" appearing in the text

mentions of the name "Anton."

No Comments

No Known Activations