INDEX

Explanations

negative descriptors referring to lack of intelligence

oai_token-act-pair · gpt-3.5-turbo

instances of the word "dumb" and related expressions of foolishness or lack of intelligence

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Lago

-0.82

 Noir

-0.72

UAL

-0.71

 Chronicles

-0.67

 Flav

-0.67

TOR

-0.65

ATURES

-0.64

________________________________________________________________

-0.63

cially

-0.63

ATURE

-0.62

POSITIVE LOGITS

founded

1.35

arton

1.17

bell

1.15

found

1.14

stru

0.96

est

0.95

asses

0.91

holes

0.91

wallet

0.89

gest

0.87

Activations Density 0.008%

negative descriptors referring to lack of intelligence

instances of the word "dumb" and related expressions of foolishness or lack of intelligence

No Comments

No Known Activations