INDEX

Explanations

phrases related to legal actions and consequences

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and their frequencies in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 conclud

-0.68

 describ

-0.66

 answ

-0.60

 grounding

-0.60

 baseline

-0.60

 aggregation

-0.59

eatures

-0.59

 prescriptions

-0.59

 concess

-0.59

 isolation

-0.58

POSITIVE LOGITS

nee

0.87

rama

0.82

etc

0.77

 Kinnikuman

0.70

uthor

0.69

icio

0.68

 supra

0.68

oshi

0.68

0.67

wait

0.67

Activations Density 0.200%

phrases related to legal actions and consequences

punctuation marks and their frequencies in the text

No Comments

No Known Activations