INDEX

Explanations

phrases related to the concept of pandering

oai_token-act-pair · gpt-3.5-turbo

references to pandas or related terminology

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

 Skydragon

-0.66

 Eisen

-0.64

LECT

-0.62

terday

-0.62

FUL

-0.60

fully

-0.59

creen

-0.59

 Lauder

-0.58

 actionGroup

-0.58

ALD

-0.57

POSITIVE LOGITS

emonium

1.65

emic

1.47

erers

1.08

elines

0.96

ering

0.95

erer

0.94

emonic

0.93

aren

0.92

eline

0.92

oor

0.91

Activations Density 0.066%

phrases related to the concept of pandering

references to pandas or related terminology

No Comments

No Known Activations