INDEX

Explanations

contractions with the form "Let's" followed by verbs or related phrases

oai_token-act-pair · gpt-3.5-turbo

phrases that begin with "Let's"

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

eur

-0.72

ELD

-0.69

etheless

-0.65

nai

-0.59

 exhibited

-0.57

forms

-0.57

 behavi

-0.56

dominated

-0.56

til

-0.56

KNOWN

-0.56

POSITIVE LOGITS

 assume

1.24

 suppose

1.20

 pretend

1.17

 recap

1.06

 simplify

1.06

 examine

1.05

 summarize

1.05

say

1.03

 presume

1.01

 ignore

0.99

Activations Density 0.028%

contractions with the form "Let's" followed by verbs or related phrases

phrases that begin with "Let's"

No Known Activations