INDEX

Explanations

words related to interpreting or interpretation

oai_token-act-pair · gpt-3.5-turbo

terms related to the act of interpretation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ccoli

-0.84

 Indust

-0.79

trap

-0.78

Interstitial

-0.72

guard

-0.70

llah

-0.69

 Empires

-0.68

ventus

-0.68

etsk

-0.67

pring

-0.67

POSITIVE LOGITS

 interpret

1.12

 Interpret

1.06

 interpretation

1.01

 interpretations

1.01

 interpreting

0.97

 interpre

0.95

ative

0.87

atively

0.87

 misinterpret

0.86

 meanings

0.84

Activations Density 0.042%

words related to interpreting or interpretation

terms related to the act of interpretation

No Comments

No Known Activations