INDEX

Explanations

phrases related to loss or disappearance

oai_token-act-pair · gpt-3.5-turbo

instances of the word "lost" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

osi

-0.74

ansky

-0.66

 intimid

-0.66

ibli

-0.63

sis

-0.62

NVIDIA

-0.60

oples

-0.60

OPLE

-0.59

arbon

-0.59

 primed

-0.59

POSITIVE LOGITS

itive

0.76

luster

0.73

lust

0.72

touch

0.71

 lost

0.70

 Souls

0.70

itaire

0.69

hearted

0.69

 sight

0.68

³

0.68

Activations Density 0.027%

phrases related to loss or disappearance

instances of the word "lost" in various contexts

No Comments

No Known Activations