INDEX

Explanations

locations or entities with the name containing "Ac"

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of "acknowledgment" or "recognition."

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

ĸļ

-0.86

ï¸ı

-0.72

 Stur

-0.71

 Shutterstock

-0.69

 Dare

-0.68

ĪĴ

-0.67

 Gemini

-0.67

 Desire

-0.66

 Burk

-0.64

backer

-0.62

POSITIVE LOGITS

rylic

1.30

oustic

1.30

ademic

1.13

rosse

1.06

upuncture

1.04

celer

1.01

anth

0.99

acia

0.98

osta

0.97

ritical

0.96

Activations Density 0.020%

locations or entities with the name containing "Ac"

words related to the concept of "acknowledgment" or "recognition."

No Comments

No Known Activations