INDEX

Explanations

special characters and symbols used in text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "he" and its variations, indicating a focus on male subjects or characters

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

 guiActiveUnfocused

-0.91

 publicity

-0.72

 Farming

-0.72

 Lunch

-0.69

 Palest

-0.65

 Libyan

-0.65

 Kenyan

-0.65

 adolesc

-0.65

 Circus

-0.64

 Salad

-0.63

POSITIVE LOGITS

dro

0.95

¹

0.94

Â¯

0.86

£

0.86

ates

0.86

Į

0.85

drivers

0.85

should

0.84

âĸº

0.84

\'

0.83

Activations Density 0.230%

special characters and symbols used in text

instances of the word "he" and its variations, indicating a focus on male subjects or characters

No Comments

No Known Activations