INDEX

Explanations

quotations and phrases with a negative connotation or critical tone

oai_token-act-pair · gpt-3.5-turbo

phrases or quotes that describe actions or characteristics attributed to entities

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

 ********************************

-0.70

mentioned

-0.65

ersen

-0.64

 accordingly

-0.64

cies

-0.64

bg

-0.60

then

-0.60

msg

-0.59

ixie

-0.59

onga

-0.59

POSITIVE LOGITS

 conduit

0.79

 distraction

0.74

 nuisance

0.72

 gateway

0.72

 legitimate

0.72

 precursor

0.69

 prerequisite

0.67

 definitive

0.67

 singular

0.66

 distinct

0.65

Activations Density 0.473%

quotations and phrases with a negative connotation or critical tone

phrases or quotes that describe actions or characteristics attributed to entities

No Known Activations