INDEX

Explanations

terms related to the word "pandering."

oai_token-act-pair · gpt-3.5-turbo

references to "pandas" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

-0.86

phabet

-0.82

LOD

-0.74

ESSION

-0.74

 Templar

-0.68

 Lauder

-0.66

ARB

-0.66

tes

-0.66

 Achievement

-0.65

 VICE

-0.65

POSITIVE LOGITS

 pand

1.34

emic

1.13

emaker

0.86

atown

0.86

emonium

0.85

wcs

0.78

elines

0.78

sty

0.75

artisan

0.75

 influenza

0.75

Activations Density 0.008%

terms related to the word "pandering."

references to "pandas" in various contexts

No Comments

No Known Activations