INDEX

Explanations

words related to the concept of 'petit' in various contexts

oai_token-act-pair · gpt-3.5-turbo

words related to pets or animals

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

 mode

-0.62

 metic

-0.58

 Arrows

-0.58

NEC

-0.57

 alternate

-0.57

rency

-0.57

 STATS

-0.56

 Bangladesh

-0.56

 disciplines

-0.55

 modes

-0.55

POSITIVE LOGITS

sels

0.89

angelo

0.86

achus

0.85

isi

0.83

asus

0.78

oshenko

0.77

culosis

0.72

istine

0.71

dinand

0.70

anamo

0.69

Activations Density 0.149%

words related to the concept of 'petit' in various contexts

words related to pets or animals

No Comments

No Known Activations