INDEX

Explanations

phrases related to providing information or instructions

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate requests for additional information

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

aud

-0.67

 Notting

-0.67

Amb

-0.65

 choir

-0.64

 Gong

-0.63

alone

-0.62

zhen

-0.62

azz

-0.61

redd

-0.61

Rated

-0.59

POSITIVE LOGITS

 regarding

0.78

 pertaining

0.75

 than

0.75

 details

0.74

ï¸ı

0.71

 relating

0.68

finder

0.68

fulness

0.68

actionDate

0.67

 info

0.67

Activations Density 0.041%

phrases related to providing information or instructions

phrases that indicate requests for additional information

No Known Activations