INDEX

Explanations

complex relationships or situations where something is hidden or under layers

oai_token-act-pair · gpt-3.5-turbo

references to concealment and hidden activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 educ

-0.69

 vetoed

-0.68

 attendance

-0.67

 buyer

-0.67

IFIED

-0.66

 geared

-0.64

 illust

-0.64

 honorary

-0.64

 boycot

-0.63

ocal

-0.62

POSITIVE LOGITS

 depths

1.20

 bushes

1.18

 trenches

1.15

 mountains

1.13

 cliffs

1.12

 tunnels

1.12

 woods

1.08

 canyon

1.08

 caves

1.07

 Mountains

1.06

Activations Density 0.722%

complex relationships or situations where something is hidden or under layers

references to concealment and hidden activities

No Comments

No Known Activations