INDEX

Explanations

words related to being the target or focus of attention or scrutiny

oai_token-act-pair · gpt-3.5-turbo

instances of the word "object" in various grammatical forms

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Leone

-0.69

teenth

-0.68

ricia

-0.68

NPR

-0.68

corn

-0.67

elsius

-0.66

fer

-0.63

 nerves

-0.63

 corrid

-0.63

ther

-0.63

POSITIVE LOGITS

ivity

1.27

ivist

1.06

ively

1.04

ivism

1.04

imus

1.00

ified

0.97

ifying

0.96

ification

0.96

ion

0.94

ifies

0.94

Activations Density 0.016%

words related to being the target or focus of attention or scrutiny

instances of the word "object" in various grammatical forms

No Known Activations