INDEX

Explanations

instances where laughter is described or implied

oai_token-act-pair · gpt-3.5-turbo

instances of laughter and related expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

fell

-0.82

ded

-0.75

cycl

-0.71

voy

-0.67

 Centauri

-0.66

ction

-0.66

establishment

-0.63

ighth

-0.62

occupied

-0.62

 mete

-0.61

POSITIVE LOGITS

Laughs

1.16

laughs

1.15

HAEL

0.85

laughter

0.82

laugh

0.81

creen

0.77

hirt

0.75

terson

0.75

swers

0.71

=-=-

0.69

Activations Density 0.013%

instances where laughter is described or implied

instances of laughter and related expressions

No Comments

No Known Activations