INDEX

Explanations

mentions of causality or influence in a cause and effect relationship

oai_token-act-pair · gpt-3.5-turbo

constructs that indicate causation or result

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

thia

-0.76

rina

-0.72

æ©Ł

-0.72

ÃĽ

-0.65

EEK

-0.64

hus

-0.63

anz

-0.63

lean

-0.63

anwhile

-0.62

nai

-0.62

POSITIVE LOGITS

 sense

1.12

hift

1.00

 sure

0.99

 navigating

0.92

it

0.91

 them

0.82

 matters

0.82

 accessing

0.79

 interacting

0.77

 transporting

0.77

Activations Density 0.085%

mentions of causality or influence in a cause and effect relationship

constructs that indicate causation or result

No Comments

No Known Activations