INDEX

Explanations

sentences that emphasize a particular concept by stating that there is nothing except for that concept

oai_token-act-pair · gpt-3.5-turbo

phrases that include the word "but."

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

achment

-0.71

igmat

-0.69

interstitial

-0.68

orc

-0.67

VERTISEMENT

-0.67

ccording

-0.66

ahime

-0.66

gged

-0.65

lication

-0.63

iliary

-0.62

POSITIVE LOGITS

tons

0.90

 fortunately

0.72

 luckily

0.71

chery

0.71

agnetic

0.65

èª

0.65

warm

0.64

 Yugoslav

0.64

ukes

0.62

 thankfully

0.59

Activations Density 0.047%

sentences that emphasize a particular concept by stating that there is nothing except for that concept

phrases that include the word "but."

No Known Activations