INDEX

Explanations

specific names or terms associated with some kind of action or event

oai_token-act-pair · gpt-3.5-turbo

occurrences of a specific term or identifier that appears frequently 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

å¥³

-0.74

 Ranger

-0.69

yards

-0.67

NetMessage

-0.67

 comparable

-0.66

 flux

-0.66

Posts

-0.66

 Willow

-0.66

ACTED

-0.65

 poppy

-0.63

POSITIVE LOGITS

ij

1.23

utsu

1.02

ournal

0.99

ohn

0.98

ordan

0.97

eh

0.96

acket

0.95

kl

0.94

iji

0.91

Ã£o

0.89

Activations Density 0.007%

specific names or terms associated with some kind of action or event

occurrences of a specific term or identifier that appears frequently in various contexts

No Comments

No Known Activations