INDEX

Explanations

expressions related to power capacity and energy generation

oai_token-act-pair · gpt-3.5-turbo

terms related to energy measurement and production

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

phrine

-0.79

handle

-0.71

netflix

-0.71

afort

-0.70

cision

-0.64

cooked

-0.63

staking

-0.63

ĺħ

-0.62

cook

-0.60

self

-0.60

POSITIVE LOGITS

ILD

1.09

GW

1.07

TW

1.03

uild

0.93

Ts

0.90

TF

0.85

ILA

0.85

MW

0.83

EEK

0.81

SW

0.80

Activations Density 0.007%

expressions related to power capacity and energy generation

terms related to energy measurement and production

No Comments

No Known Activations