INDEX

Explanations

mentions of the word "Interior"

oai_token-act-pair · gpt-3.5-turbo

references to government departments, specifically the Interior

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

cgi

-0.72

fleet

-0.69

owder

-0.67

-0.65

yrs

-0.65

omen

-0.65

fortune

-0.64

amins

-0.64

ap

-0.64

asters

-0.63

POSITIVE LOGITS

 Interior

1.21

 ministry

0.94

 Ministry

0.90

 interior

0.83

 Minister

0.79

ashtra

0.77

 minister

0.77

 decoration

0.76

door

0.73

eering

0.72

Activations Density 0.004%

mentions of the word "Interior"

references to government departments, specifically the Interior

No Comments

No Known Activations