INDEX

Explanations

occurrences of the word "Modi" in the text

oai_token-act-pair · gpt-3.5-turbo

mentions of Narendra Modi

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

 Beir

-0.78

 CLIENT

-0.72

 Niet

-0.69

cuts

-0.68

 Marilyn

-0.67

 Jacksonville

-0.67

AGES

-0.66

ritch

-0.64

ELF

-0.64

SPL

-0.62

POSITIVE LOGITS

 Modi

0.94

Å¡

0.77

 Jinping

0.77

abad

0.76

urai

0.75

Quantity

0.74

ulus

0.74

agara

0.74

Äĩ

0.73

pour

0.71

Activations Density 0.017%

occurrences of the word "Modi" in the text

mentions of Narendra Modi

No Comments

No Known Activations