INDEX

Explanations

phrases related to secret agents or espionage activities

oai_token-act-pair · gpt-3.5-turbo

references to agents or authoritative figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

issance

-1.09

lihood

-1.03

etooth

-0.83

FACE

-0.82

orld

-0.74

ĸļ

-0.69

phrine

-0.67

cept

-0.66

nz

-0.65

imeo

-0.64

POSITIVE LOGITS

 prov

0.94

 agent

0.94

sov

0.86

 agents

0.85

 Agent

0.85

agent

0.85

agents

0.83

arial

0.78

osa

0.78

 Agents

0.78

Activations Density 0.030%

phrases related to secret agents or espionage activities

references to agents or authoritative figures

No Comments

No Known Activations