INDEX

Explanations

phrases or sentences that contain the word "simple"

oai_token-act-pair · gpt-3.5-turbo

references to simplicity in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

âĹ¼

-0.81

 largeDownload

-0.73

 Experts

-0.71

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.69

 reckoned

-0.67

hips

-0.65

vance

-0.65

 hemor

-0.64

MIC

-0.63

amen

-0.61

POSITIVE LOGITS

tons

1.18

 simple

0.95

wallet

0.95

 straightforward

0.88

json

0.88

minded

0.86

simple

0.82

ified

0.78

 syrup

0.78

lly

0.78

Activations Density 0.020%

phrases or sentences that contain the word "simple"

references to simplicity in various contexts

No Comments

No Known Activations