INDEX

Explanations

references to movement or direction, particularly the word "down"

oai_token-act-pair · gpt-3.5-turbo

directional terms related to movement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ãĥİ

-0.64

 positives

-0.63

aneous

-0.61

acea

-0.60

 reass

-0.59

 Greeks

-0.59

Í

-0.59

 backdrop

-0.58

 Remastered

-0.58

 Advantage

-0.58

POSITIVE LOGITS

river

1.18

 stairs

1.18

stairs

1.12

wind

1.04

range

1.02

 onto

0.90

 into

0.90

market

0.90

 hill

0.90

grading

0.89

Activations Density 0.065%

references to movement or direction, particularly the word "down"

directional terms related to movement

No Comments

No Known Activations