INDEX

Explanations

proper nouns related to organizations or entities

oai_token-act-pair · gpt-3.5-turbo

names and terms associated with specific brands, companies, or notable entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

rising

-0.67

GGGG

-0.63

!:

-0.63

IPM

-0.63

:,

-0.63

WARD

-0.63

orget

-0.63

theless

-0.62

EStream

-0.61

 Solution

-0.61

POSITIVE LOGITS

 lacks

1.35

 hadn

1.26

 hasn

1.23

 exists

1.17

 resides

1.14

 prefers

1.14

isn

1.14

 lacked

1.13

 doesn

1.12

 existed

1.12

Activations Density 0.577%

proper nouns related to organizations or entities

names and terms associated with specific brands, companies, or notable entities

No Comments

No Known Activations