INDEX

Explanations

words related to conflict or strife

oai_token-act-pair · gpt-3.5-turbo

instances of the word "tension" and its variations, indicating conflict or strain

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

prints

-0.75

issance

-0.73

glas

-0.70

cise

-0.69

icles

-0.69

sites

-0.68

option

-0.68

icle

-0.67

sure

-0.67

Interstitial

-0.66

POSITIVE LOGITS

 tension

0.93

 cooker

0.88

 tensions

0.85

 flared

0.79

 reliever

0.76

 escalation

0.75

 boil

0.74

bh

0.73

yip

0.72

rained

0.72

Activations Density 0.021%

words related to conflict or strife

instances of the word "tension" and its variations, indicating conflict or strain

No Comments

No Known Activations