INDEX

Explanations

references to articles or pieces of written content

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "article" 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

cffff

-0.93

cffffcc

-0.84

 Nadu

-0.73

elsius

-0.72

pter

-0.72

²¾

-0.72

NetMessage

-0.70

edient

-0.68

ersen

-0.67

¬¼

-0.66

POSITIVE LOGITS

meal

1.18

 articles

0.89

 published

0.82

 article

0.81

riage

0.77

 titled

0.77

 editor

0.75

 detailing

0.75

orial

0.73

Meta

0.73

Activations Density 0.030%

references to articles or pieces of written content

mentions of the term "article" in various contexts

No Comments

No Known Activations