INDEX

Explanations

mentions of the name "Sharon"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Shar" and its variations 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

REDACTED

-0.79

hiro

-0.70

 Upton

-0.69

é¾įå¥ĳå£«

-0.67

 Uran

-0.67

asus

-0.65

landish

-0.65

ATS

-0.64

orget

-0.63

GROUND

-0.63

POSITIVE LOGITS

pton

1.22

ples

1.07

riors

1.03

ning

1.02

pless

1.01

pling

1.00

ãĥ£

1.00

ply

0.95

ps

0.93

pering

0.90

Activations Density 0.024%

mentions of the name "Sharon"

mentions of the name "Shar" and its variations in various contexts

No Comments

No Known Activations