INDEX

Explanations

references to the NSA (National Security Agency) in documents

oai_token-act-pair · gpt-3.5-turbo

mentions of the National Security Agency (NSA)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

interstitial

-0.80

cause

-0.73

hani

-0.72

 Camb

-0.70

uces

-0.69

ragon

-0.67

Cue

-0.66

lihood

-0.66

hips

-0.65

odge

-0.64

POSITIVE LOGITS

 whistleblower

1.05

NSA

1.04

 spying

0.93

IDs

0.89

ionage

0.84

 Accountability

0.78

 surveillance

0.77

 contractor

0.75

HQ

0.75

ILS

0.75

Activations Density 0.025%

references to the NSA (National Security Agency) in documents

mentions of the National Security Agency (NSA)

No Comments

No Known Activations