INDEX

Explanations

sequences of letters in a specific pattern, possibly related to a particular language or code

oai_token-act-pair · gpt-3.5-turbo

Cyrillic characters in text

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

ichita

-0.89

merce

-0.88

undai

-0.85

kins

-0.85

kson

-0.83

geries

-0.81

atche

-0.80

perature

-0.80

ffer

-0.75

eanor

-0.73

POSITIVE LOGITS

Ð¸

1.11

Ð¾Ð

1.09

Ð°

1.07

ÑĤ

1.03

Ð¾

0.99

Ñ

0.92

Ð½

0.92

Ðµ

0.92

Ðº

0.90

Ñĭ

0.89

Activations Density 0.016%

sequences of letters in a specific pattern, possibly related to a particular language or code

Cyrillic characters in text

No Comments

No Known Activations