INDEX

Explanations

suspicious activities or objects

oai_token-act-pair · gpt-3.5-turbo

the word "suspicious" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

apsed

-0.76

skill

-0.75

 taught

-0.70

ankind

-0.70

á

-0.69

learning

-0.68

hung

-0.67

multipl

-0.67

produced

-0.67

lished

-0.66

POSITIVE LOGITS

ly

1.25

ively

0.92

 suspicious

0.91

LY

0.87

 suspic

0.84

liness

0.81

eties

0.81

lys

0.80

uously

0.78

 Activity

0.77

Activations Density 0.019%

suspicious activities or objects

the word "suspicious" and its variations in different contexts

No Comments

No Known Activations