INDEX

Explanations

quantitative descriptions or numbers related to groups of people

oai_token-act-pair · gpt-3.5-turbo

references to large groups of people or populations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

imaru

-0.74

odox

-0.69

erenn

-0.67

ilyn

-0.65

 causation

-0.63

ħĭ

-0.63

pai

-0.63

inventoryQuantity

-0.61

 protocol

-0.60

 ausp

-0.59

POSITIVE LOGITS

 worldwide

0.81

votes

0.79

 crammed

0.76

 acres

0.74

pees

0.74

abytes

0.72

 annually

0.72

illion

0.71

 nationwide

0.70

 collectively

0.70

Activations Density 0.514%

quantitative descriptions or numbers related to groups of people

references to large groups of people or populations

No Comments

No Known Activations