INDEX

Explanations

phrases indicating a state or occurrence happening or being true

oai_token-act-pair · gpt-3.5-turbo

statements that indicate applicability or validity of claims or theories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ICO

-0.62

tten

-0.62

heit

-0.62

});

-0.59

>[

-0.57

)))

-0.56

 Monstrous

-0.56

 Released

-0.56

 Encyclopedia

-0.56

urus

-0.56

POSITIVE LOGITS

 everywhere

1.11

 chiefly

1.11

 especially

1.09

 mainly

1.07

 wherever

1.06

 primarily

1.05

 irrespective

1.04

especially

1.02

 principally

1.01

 regardless

1.00

Activations Density 0.451%

phrases indicating a state or occurrence happening or being true

statements that indicate applicability or validity of claims or theories

No Comments

No Known Activations