INDEX

Explanations

locations or spaces inside larger entities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Inside," indicating a focus on content related to being within a particular context or location

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enegger

-0.83

eday

-0.77

olk

-0.75

uct

-0.74

lda

-0.72

yah

-0.71

ministic

-0.71

tle

-0.69

fortune

-0.67

enez

-0.67

POSITIVE LOGITS

vert

0.85

 parentheses

0.79

 bedrooms

0.74

doors

0.71

 workings

0.70

 chambers

0.67

 latex

0.66

tains

0.66

ocent

0.64

 Marble

0.64

Activations Density 0.023%

locations or spaces inside larger entities

instances of the word "Inside," indicating a focus on content related to being within a particular context or location

No Comments

No Known Activations