INDEX

Explanations

mentions of the term "Ten"

oai_token-act-pair · gpt-3.5-turbo

references to the number "Ten."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Downloadha

-0.77

EStream

-0.67

unct

-0.66

 mileage

-0.64

Ø©

-0.64

drm

-0.63

****************

-0.63

cffffcc

-0.62

vertisement

-0.59

wi

-0.59

POSITIVE LOGITS

zin

1.07

acity

1.05

Ten

0.89

 Thousand

0.89

eta

0.88

ney

0.87

aciously

0.87

acious

0.84

Thirty

0.80

Ten

0.80

Activations Density 0.008%

mentions of the term "Ten"

references to the number "Ten."

No Comments

No Known Activations