INDEX

Explanations

phrases related to categorization or classification

oai_token-act-pair · gpt-3.5-turbo

references to categories and classifications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eeds

-0.67

 advances

-0.65

displayText

-0.61

 nipples

-0.60

facts

-0.59

 noises

-0.57

released

-0.57

 visits

-0.56

 taped

-0.56

 reconnect

-0.56

POSITIVE LOGITS

 category

1.90

 categories

1.51

ategory

1.37

category

1.35

 bracket

1.19

 tier

1.14

 Category

1.08

 grouping

1.08

 Categories

1.06

 group

1.05

Activations Density 0.397%

phrases related to categorization or classification

references to categories and classifications

No Comments

No Known Activations