INDEX

Explanations

contrasting statements or elements within text

oai_token-act-pair · gpt-3.5-turbo

negating phrases that start with "nor."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

trap

-0.70

edu

-0.69

imil

-0.67

Premium

-0.66

AGE

-0.65

AGES

-0.64

UP

-0.64

Package

-0.64

 Breach

-0.62

Dir

-0.59

POSITIVE LOGITS

wegian

1.14

hovah

1.02

acle

0.89

Else

0.85

acles

0.85

withstanding

0.83

soever

0.83

nor

0.81

chid

0.80

 Judah

0.79

Activations Density 0.008%

contrasting statements or elements within text

negating phrases that start with "nor."

No Comments

No Known Activations