INDEX

Explanations

words related to mainstream media and geographical locations

oai_token-act-pair · gpt-3.5-turbo

terms related to media and geographical locations

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

 Canaver

-0.69

cific

-0.66

pedia

-0.65

 Byrne

-0.63

tnc

-0.62

 Klux

-0.62

 empath

-0.62

igslist

-0.61

 Rhod

-0.60

sol

-0.59

POSITIVE LOGITS

eele

0.71

rollers

0.70

($)

0.70

hander

0.69

roller

0.67

 Nope

0.66

pants

0.65

 Jacket

0.64

 Moff

0.63

loader

0.62

Activations Density 0.055%

words related to mainstream media and geographical locations

terms related to media and geographical locations

No Comments

No Known Activations