INDEX

Explanations

phrases related to protection or security

oai_token-act-pair · gpt-3.5-turbo

terms related to protection and safety measures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

lins

-0.76

gered

-0.73

NetMessage

-0.70

bender

-0.70

ergy

-0.68

chrome

-0.66

ctory

-0.65

hl

-0.64

kell

-0.64

 clay

-0.64

POSITIVE LOGITS

 safeguards

1.01

 safegu

0.96

 safeguard

0.93

 protecting

0.90

saf

0.83

 guarding

0.82

 Protect

0.81

raints

0.81

 shielding

0.80

 protects

0.80

Activations Density 0.018%

phrases related to protection or security

terms related to protection and safety measures

No Comments

No Known Activations