INDEX

Explanations

mentions of the word "psycho" or derivatives like "psychoactive"

oai_token-act-pair · gpt-3.5-turbo

terms related to psychoactive substances and their effects

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

RL

-0.69

arians

-0.68

ICAN

-0.68

HCR

-0.67

ership

-0.67

shire

-0.66

illary

-0.64

owship

-0.63

BMC

-0.63

 Lions

-0.63

POSITIVE LOGITS

analysis

1.07

active

0.91

gressive

0.90

chedel

0.87

ppy

0.81

 psycho

0.79

 absor

0.79

spective

0.79

oke

0.78

ãĥĦ

0.76

Activations Density 0.015%

mentions of the word "psycho" or derivatives like "psychoactive"

terms related to psychoactive substances and their effects

No Comments

No Known Activations