INDEX

Explanations

phrases related to driving forces or motivations

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate causation or motivation

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

enegger

-0.71

 vantage

-0.66

antage

-0.64

 pads

-0.64

 Kinnikuman

-0.64

akings

-0.64

eport

-0.63

 Canad

-0.63

umbn

-0.62

alon

-0.61

POSITIVE LOGITS

by

0.95

BY

0.90

by

0.88

Ń·

0.81

 solely

0.80

 principally

0.77

By

0.76

 aback

0.75

By

0.74

 destro

0.73

Activations Density 0.154%

phrases related to driving forces or motivations

phrases that indicate causation or motivation

No Comments

No Known Activations