INDEX

Explanations

instances where the word "itself" is used

oai_token-act-pair · gpt-3.5-turbo

the word "itself" in various contexts

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

ammy

-0.65

onal

-0.64

ysical

-0.62

VK

-0.60

 Wire

-0.60

CLOSE

-0.60

Dispatch

-0.59

 Federation

-0.59

 Miko

-0.58

MER

-0.57

POSITIVE LOGITS

é¾įåĸļå£«

0.83

 acknowledges

0.74

 admits

0.74

has

0.70

 qualifies

0.70

 constitutes

0.68

ãĥķãĤ©

0.67

 attest

0.67

contained

0.66

 contains

0.66

Activations Density 0.056%

instances where the word "itself" is used

the word "itself" in various contexts

No Comments

No Known Activations