INDEX

Explanations

mentions of locations or places

oai_token-act-pair · gpt-3.5-turbo

references to "spot" or instances where something is highlighted or emphasized

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

issance

-0.82

yss

-0.65

racuse

-0.64

velt

-0.61

 pend

-0.61

jri

-0.59

ÄŁ

-0.59

wake

-0.59

 Miko

-0.58

 adolesc

-0.58

POSITIVE LOGITS

lights

1.65

light

1.13

ter

1.12

lighting

1.05

ters

1.03

ty

1.00

ting

0.97

tery

0.96

pots

0.95

lot

0.90

Activations Density 0.042%

mentions of locations or places

references to "spot" or instances where something is highlighted or emphasized

No Comments

No Known Activations