INDEX

Explanations

instances of the character 'Ļ'

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

proper nouns or named entities

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 partnerships

-0.69

izen

-0.65

 township

-0.65

 notebooks

-0.64

geries

-0.64

 detection

-0.62

iage

-0.60

sels

-0.59

 range

-0.59

 Cell

-0.59

POSITIVE LOGITS

ï¸ı

1.17

VERTISEMENT

0.96

ï¸

0.93

fter

0.83

CHR

0.82

orean

0.80

âģ

0.79

Â·Â·

0.77

audi

0.76

Â½

0.76

Activations Density 0.123%

instances of the character 'Ļ'

proper nouns or named entities

No Comments

No Known Activations