INDEX

Explanations

phrases related to "Jack the Ripper."

oai_token-act-pair · gpt-3.5-turbo

repeated references to the word "ipper," indicating a focus on characters or entities related to that term

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

¿½

-0.95

ADRA

-0.87

rade

-0.73

ãĤ£

-0.70

places

-0.69

Yel

-0.69

cn

-0.69

hemat

-0.67

©¶æ

-0.65

³

-0.65

POSITIVE LOGITS

ipper

0.97

iness

0.90

clips

0.90

ily

0.87

maid

0.84

chief

0.80

jack

0.71

olean

0.71

llan

0.69

aired

0.69

Activations Density 0.023%

phrases related to "Jack the Ripper."

repeated references to the word "ipper," indicating a focus on characters or entities related to that term

No Comments

No Known Activations