INDEX

Explanations

phrases indicating a significant change or transformation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "changed" and its variations

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

amina

-0.87

mination

-0.79

alty

-0.76

 DRAGON

-0.76

ç«

-0.75

stra

-0.67

AFB

-0.66

Ranked

-0.64

-+-+

-0.64

PLIED

-0.63

POSITIVE LOGITS

ĸļ

1.04

atile

0.72

 drastically

0.72

 radically

0.72

 effected

0.70

imedia

0.70

 hands

0.70

elvet

0.70

changed

0.69

wre

0.69

Activations Density 0.042%

phrases indicating a significant change or transformation

instances of the word "changed" and its variations

No Comments

No Known Activations