INDEX

Explanations

words related to rules, regulations, and organizational procedures

oai_token-act-pair · gpt-3.5-turbo

connections between policies and their impacts on various societal aspects

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

culus

-0.81

Ĥİ

-0.71

 Craw

-0.65

ibal

-0.65

wolf

-0.64

 Toledo

-0.64

cise

-0.64

 Cruiser

-0.63

azz

-0.63

nee

-0.63

POSITIVE LOGITS

 practices

1.14

 beliefs

1.12

 philosophies

1.11

 ideologies

1.09

 personalities

1.08

 behaviours

1.04

 behaviors

1.04

 feelings

1.03

 actions

1.02

 motivations

1.02

Activations Density 0.277%

words related to rules, regulations, and organizational procedures

connections between policies and their impacts on various societal aspects

No Comments

No Known Activations