INDEX

Explanations

phrases related to actions or events happening, especially with specific numbers or measures involved

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a comparison or condition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Rub

-0.72

rous

-0.69

ivas

-0.68

ople

-0.67

itiveness

-0.67

audi

-0.64

eeee

-0.64

leness

-0.63

rolet

-0.61

rol

-0.60

POSITIVE LOGITS

piring

1.09

phy

1.06

pects

1.04

 opposed

1.02

pired

1.02

ynchron

1.00

 well

0.97

 follows

0.97

 evidenced

0.92

pires

0.92

Activations Density 0.184%

phrases related to actions or events happening, especially with specific numbers or measures involved

phrases indicating a comparison or condition

No Comments

No Known Activations