INDEX

Explanations

words related to psychological or emotional development and relationships

oai_token-act-pair · gpt-3.5-turbo

phrases and terms related to development and relationships

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

isSpecialOrderable

-0.78

Joined

-0.75

ģĸ

-0.70

 rightfully

-0.70

autions

-0.66

 sender

-0.66

 Mehran

-0.65

 Macy

-0.64

elected

-0.63

aunting

-0.62

POSITIVE LOGITS

 skills

0.77

 techniques

0.73

enegger

0.73

 breakthrough

0.73

VK

0.71

 technique

0.71

 strategy

0.71

 traction

0.70

 technologies

0.70

 trajectory

0.70

Activations Density 0.218%

words related to psychological or emotional development and relationships

phrases and terms related to development and relationships

No Comments

No Known Activations