INDEX

Explanations

names containing the substring "wan."

oai_token-act-pair · gpt-3.5-turbo

instances of the name "Marwan"

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

 liability

-0.71

ensed

-0.69

 mileage

-0.67

 clustered

-0.67

£ı

-0.67

İĭ

-0.64

 leaflets

-0.63

ttle

-0.63

 defiance

-0.63

 imperative

-0.63

POSITIVE LOGITS

igans

1.08

 Kenobi

1.03

igan

1.02

hao

1.01

wan

0.94

loo

0.94

wu

0.93

artz

0.90

nee

0.90

ryu

0.89

Activations Density 0.012%

names containing the substring "wan."

instances of the name "Marwan"

No Comments

No Known Activations