INDEX

Explanations

words related to protection and defense

oai_token-act-pair · gpt-3.5-turbo

references to protective barriers or defensive mechanisms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

•Sports-related features

nres

No Comments

Negative Logits

gres

-0.81

iasco

-0.76

pheus

-0.71

ĸļ

-0.69

————————

-0.68

ribune

-0.68

cause

-0.68

lihood

-0.67

 Helpful

-0.66

orie

-0.65

POSITIVE LOGITS

heed

0.83

 shield

0.79

 piercing

0.78

 shields

0.78

lain

0.77

 absorbing

0.77

buster

0.74

 shielded

0.73

 shielding

0.71

 erected

0.71

Activations Density 0.064%

words related to protection and defense

references to protective barriers or defensive mechanisms

No Comments

No Known Activations