INDEX

Explanations

names or terms related to Spanish language and culture

oai_token-act-pair · gpt-3.5-turbo

the special character "ñ"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

mble

-0.72

clusive

-0.67

 MISS

-0.67

HEAD

-0.66

fare

-0.64

 decomp

-0.63

 Vance

-0.62

 SPACE

-0.62

 Fantastic

-0.62

 Sussex

-0.61

POSITIVE LOGITS

ez

1.07

Ã±

0.95

Ã±a

0.94

rez

0.91

Ã³n

0.85

Ã£

0.81

Ģ

0.78

untu

0.78

esian

0.77

oz

0.76

Activations Density 0.049%

names or terms related to Spanish language and culture

the special character "ñ"

No Comments

No Known Activations