INDEX

Explanations

proper nouns, particularly related to technology and organizations

oai_token-act-pair · gpt-3.5-turbo

placeholders or markers indicating new sections or elements in writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

enegger

-0.90

anwhile

-0.57

mble

-0.55

 convey

-0.52

 dummy

-0.52

ä»£

-0.51

cyn

-0.50

 dividing

-0.50

 spirited

-0.49

 wiser

-0.49

POSITIVE LOGITS

Coin

0.92

coin

0.76

Wiki

0.74

Forge

0.71

Game

0.71

Bot

0.69

 Brewing

0.69

Tech

0.69

Fest

0.68

Server

0.67

Activations Density 0.619%

proper nouns, particularly related to technology and organizations

placeholders or markers indicating new sections or elements in writing

No Comments

No Known Activations