INDEX

Explanations

references to the food item "beef."

oai_token-act-pair · gpt-3.5-turbo

mentions of beef 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 @ 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

âĸ¬

-0.84

pmwiki

-0.82

 Sloan

-0.72

 Scotia

-0.68

SPONSORED

-0.65

 Brighton

-0.63

PV

-0.63

 Archangel

-0.62

hematic

-0.62

âĸ¬âĸ¬

-0.62

POSITIVE LOGITS

cake

1.30

ington

1.01

jer

0.98

 beef

0.93

alos

0.91

bean

0.90

skin

0.90

meat

0.89

cakes

0.88

ste

0.87

Activations Density 0.011%

references to the food item "beef."

mentions of beef in various contexts

No Comments

No Known Activations