INDEX

Explanations

phrases related to inclusivity and unity

oai_token-act-pair · gpt-3.5-turbo

terms related to inclusivity and social inclusion

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

acca

-0.79

ascus

-0.75

riter

-0.74

entanyl

-0.74

CLASSIFIED

-0.73

udder

-0.73

attr

-0.73

nit

-0.70

flies

-0.70

thur

-0.69

POSITIVE LOGITS

 minded

0.95

 inclusive

0.92

iveness

0.85

mble

0.72

ively

0.71

galitarian

0.68

clus

0.68

clusive

0.68

tions

0.67

 spaces

0.67

Activations Density 0.016%

phrases related to inclusivity and unity

terms related to inclusivity and social inclusion

No Comments

No Known Activations