INDEX

Explanations

the word "pandering."

oai_token-act-pair · gpt-3.5-turbo

references to pandas and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pell

-0.72

FUL

-0.71

LECT

-0.71

creen

-0.70

 Templar

-0.70

terday

-0.69

pelling

-0.69

ESSION

-0.68

 Skydragon

-0.68

 Eisen

-0.66

POSITIVE LOGITS

emonium

1.45

emic

1.34

 pand

1.12

 Pand

0.89

erers

0.87

aren

0.86

Pand

0.85

rophe

0.85

emaker

0.85

erer

0.83

Activations Density 0.018%

the word "pandering."

references to pandas and related terms

No Comments

No Known Activations