INDEX

Explanations

words related to numerical increase or positive change

oai_token-act-pair · gpt-3.5-turbo

statistical measurements and data trends

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

Not in Any Lists

No Comments

Negative Logits

å½

-0.70

uala

-0.70

rich

-0.69

RAW

-0.67

athered

-0.65

Bul

-0.65

CHAT

-0.62

abilities

-0.61

è»

-0.61

Design

-0.60

POSITIVE LOGITS

flation

0.91

osponsors

0.73

 heels

0.72

amon

0.70

ibaba

0.69

ahime

0.67

 comparing

0.66

ioxide

0.66

than

0.64

brainer

0.64

Activations Density 0.331%

words related to numerical increase or positive change

statistical measurements and data trends

No Comments

No Known Activations