INDEX

Explanations

phrases related to hacking or cyber attacks

oai_token-act-pair · gpt-3.5-turbo

references to hacking incidents

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

BuyableInstoreAndOnline

-0.76

inances

-0.69

zl

-0.68

imental

-0.68

ais

-0.68

cil

-0.66

 Veter

-0.65

coat

-0.65

hani

-0.63

Animal

-0.63

POSITIVE LOGITS

 hacked

0.88

 penetrated

0.87

ionage

0.84

 infiltrated

0.81

 hacking

0.77

 threats

0.75

 blackmail

0.74

 victims

0.74

 breached

0.74

 stolen

0.73

Activations Density 0.032%

phrases related to hacking or cyber attacks

references to hacking incidents

No Known Activations