INDEX

Explanations

phrases indicating a superlative ranking or comparison

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a quantifiable or notable distinction or status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

eret

-0.83

ONS

-0.75

itures

-0.65

iture

-0.63

 dstg

-0.62

atto

-0.62

[+

-0.62

Translation

-0.62

osponsors

-0.61

orrow

-0.60

POSITIVE LOGITS

 deadliest

0.86

 hottest

0.85

 finest

0.80

 America

0.78

 quir

0.78

 coolest

0.77

America

0.76

 highest

0.73

 twentieth

0.72

 greatest

0.71

Activations Density 0.124%

phrases indicating a superlative ranking or comparison

phrases that indicate a quantifiable or notable distinction or status

No Comments

No Known Activations