INDEX

Explanations

mentions of the term "over," often related to hangovers or advantages

oai_token-act-pair · gpt-3.5-turbo

the word "over" in various contexts and forms, suggesting a focus on the concept of excess or repetition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

uments

-0.71

ãĥ£

-0.70

ophile

-0.69

udes

-0.68

risome

-0.68

onna

-0.67

illary

-0.66

Â¯Â¯Â¯Â¯

-0.65

ãĥ¼ãĥĨãĤ£

-0.64

ulet

-0.63

POSITIVE LOGITS

ride

0.96

haul

0.91

lord

0.90

whelming

0.89

drive

0.88

leaf

0.87

lords

0.86

lay

0.86

stable

0.85

due

0.80

Activations Density 0.025%

mentions of the term "over," often related to hangovers or advantages

the word "over" in various contexts and forms, suggesting a focus on the concept of excess or repetition

No Comments

No Known Activations