INDEX

Explanations

phrases related to changing one's mind

oai_token-act-pair · gpt-3.5-turbo

phrases and terms related to changing opinions or beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

fill

-0.69

negie

-0.67

 ripe

-0.67

osher

-0.65

mith

-0.64

nis

-0.61

 deserving

-0.61

parser

-0.60

FUN

-0.60

æĺ¯

-0.59

POSITIVE LOGITS

emort

0.91

Ĥİ

0.71

ifice

0.70

geist

0.70

issions

0.70

Saharan

0.68

ipolar

0.67

 Centauri

0.66

 focus

0.66

Ń·

0.64

Activations Density 0.458%

phrases related to changing one's mind

phrases and terms related to changing opinions or beliefs

No Comments

No Known Activations