INDEX

Explanations

the word "same."

oai_token-act-pair · gpt-3.5-turbo

repetitive phrasing indicating similarity or equivalence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ase

-0.69

Frag

-0.68

urally

-0.67

icum

-0.67

TOR

-0.66

Interstitial

-0.65

*=-

-0.65

ä¿

-0.65

-0.63

ickets

-0.62

POSITIVE LOGITS

 vein

0.88

 thing

0.87

 exact

0.82

 playbook

0.76

 fate

0.75

 reason

0.70

 kind

0.70

 amount

0.69

 applies

0.67

 principle

0.67

Activations Density 0.046%

the word "same."

repetitive phrasing indicating similarity or equivalence

No Comments

No Known Activations