INDEX

Explanations

adjectives related to judgment or assessment

oai_token-act-pair · gpt-3.5-turbo

phrases indicating perceptions of reality, contrasting beliefs, or contradictory statements

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

istries

-0.73

 partName

-0.72

cies

-0.71

imore

-0.70

tails

-0.68

ispers

-0.68

edin

-0.67

umption

-0.67

imer

-0.66

iland

-0.66

POSITIVE LOGITS

ellectual

0.72

"'

0.69

 "âĢ¦

0.69

 imped

0.68

 inferior

0.67

 superior

0.67

0.66

 unworthy

0.64

BuyableInstoreAndOnline

0.62

 practicable

0.62

Activations Density 0.248%

adjectives related to judgment or assessment

phrases indicating perceptions of reality, contrasting beliefs, or contradictory statements

No Comments

No Known Activations