INDEX

Explanations

terms related to the concept of "occupation" or "occupying."

oai_token-act-pair · gpt-3.5-turbo

terms related to occupations and hazardous substances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Byrne

-0.62

 Sigma

-0.62

 Teresa

-0.60

 Fargo

-0.59

 constellation

-0.59

 Oaks

-0.58

 fixme

-0.58

-0.57

 Isle

-0.57

 Basin

-0.57

POSITIVE LOGITS

estate

1.33

ational

1.29

ation

1.26

ename

1.25

ers

1.25

ations

1.23

ables

1.18

ability

1.16

ants

1.15

eway

1.14

Activations Density 0.146%

terms related to the concept of "occupation" or "occupying."

terms related to occupations and hazardous substances

No Comments

No Known Activations