INDEX

Explanations

specific mentions of "Mod" followed by a number (e.g. Mod 10) in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to "Mod" as it relates to various systems or entities, likely indicating modifications or models in a specific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

FORE

-0.85

ģĸ

-0.82

éĽ

-0.79

âĸ¬

-0.77

 Lauder

-0.75

¬¼

-0.73

YA

-0.72

 Cornell

-0.72

holding

-0.72

 PRESS

-0.71

POSITIVE LOGITS

ules

1.19

icum

1.03

ifiers

1.02

ifications

0.99

ding

0.98

achev

0.96

ifier

0.96

ajo

0.96

aton

0.94

iator

0.94

Activations Density 0.008%

specific mentions of "Mod" followed by a number (e.g. Mod 10) in various contexts

references to "Mod" as it relates to various systems or entities, likely indicating modifications or models in a specific context

No Comments

No Known Activations