INDEX

Explanations

words related to jeopardizing or endangering something

oai_token-act-pair · gpt-3.5-turbo

terms related to jeopardy or risk to safety and security

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

è¦ļéĨĴ

-0.86

imb

-0.65

agn

-0.62

ann

-0.62

rikes

-0.61

gat

-0.61

 likes

-0.60

row

-0.59

iterator

-0.59

Sher

-0.59

POSITIVE LOGITS

 jeopard

1.20

 adolesc

1.02

 endanger

0.90

 undermin

0.74

 compromising

0.73

 Qiao

0.72

 comprom

0.67

ashtra

0.67

 certs

0.67

 unnecess

0.66

Activations Density 0.016%

words related to jeopardizing or endangering something

terms related to jeopardy or risk to safety and security

No Comments

No Known Activations