INDEX

Explanations

terms related to harmony or harmonious situations

oai_token-act-pair · gpt-3.5-turbo

terms related to harmony and balance

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

kamp

-0.85

asel

-0.83

ggle

-0.79

het

-0.72

oggle

-0.72

Ultra

-0.71

JV

-0.68

oggles

-0.68

ubb

-0.65

acons

-0.65

POSITIVE LOGITS

baum

0.85

 harmon

0.77

 ILCS

0.74

forth

0.72

 balances

0.72

itarian

0.72

 tune

0.72

ufact

0.71

nah

0.67

 Balanced

0.67

Activations Density 0.087%

terms related to harmony or harmonious situations

terms related to harmony and balance

No Comments

No Known Activations