INDEX

Explanations

references to the country "Iran"

oai_token-act-pair · gpt-3.5-turbo

mentions of Iran

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 LAPD

-0.76

illard

-0.75

 Niet

-0.74

inances

-0.73

 Trafford

-0.71

 gorilla

-0.67

 Odin

-0.65

opa

-0.64

DV

-0.63

imore

-0.63

POSITIVE LOGITS

 Revolutionary

0.94

 Tehran

0.85

ollah

0.85

 nuclear

0.84

 Contra

0.83

 Rouhani

0.82

 Nuclear

0.81

uclear

0.80

ibi

0.80

abad

0.80

Activations Density 0.031%

references to the country "Iran"

mentions of Iran

No Comments

No Known Activations