INDEX

Explanations

phrases related to large groups or populations of people

oai_token-act-pair · gpt-3.5-turbo

phrases indicating large populations or groups of individuals affected by various issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

inventoryQuantity

-0.78

apego

-0.69

escription

-0.67

 annexation

-0.65

 Guru

-0.63

qus

-0.59

veyard

-0.59

ILA

-0.58

umping

-0.57

cknow

-0.57

POSITIVE LOGITS

who

1.06

 irrespective

1.02

 alike

0.99

 regardless

0.96

 worldwide

0.93

 whom

0.91

 whose

0.89

 besides

0.87

 imaginable

0.83

 nationwide

0.81

Activations Density 0.311%

phrases related to large groups or populations of people

phrases indicating large populations or groups of individuals affected by various issues

No Comments

No Known Activations