INDEX

Explanations

mentions of "We" in sentences

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "We" 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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

cedes

-0.73

comes

-0.72

Textures

-0.69

pires

-0.68

imum

-0.67

 attm

-0.67

oku

-0.61

 ARTICLE

-0.61

rawdownloadcloneembedreportprint

-0.60

Untitled

-0.59

POSITIVE LOGITS

're

1.15

 evacuated

1.04

've

1.02

 apologise

1.01

 advise

0.98

 anticipate

0.98

 received

0.96

 apologize

0.93

 believe

0.92

 appreciate

0.92

Activations Density 0.176%

mentions of "We" in sentences

the presence of the word "We" in various contexts

No Comments

No Known Activations