INDEX

Explanations

phrases related to controversial topics and opinions

oai_token-act-pair · gpt-3.5-turbo

phrases related to consequences or negative outcomes of actions

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

 sled

-0.67

 Manhattan

-0.65

isode

-0.65

 Somerset

-0.64

 antip

-0.62

 Paran

-0.61

 unmarked

-0.61

ifications

-0.59

 board

-0.59

?)

-0.58

POSITIVE LOGITS

¬

1.24

¡

1.16

Ļ

1.09

Ĵ

1.09

¤

1.08

µ

1.05

ı

1.05

£

1.01

ľ

1.00

¼

0.99

Activations Density 0.343%

phrases related to controversial topics and opinions

phrases related to consequences or negative outcomes of actions

No Comments

No Known Activations