INDEX

Explanations

the letter "n" followed by a digit, often associated with numerical values or identifiers

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'n'

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

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

gerald

-0.67

 compe

-0.65

å§«

-0.62

Vaj

-0.61

espie

-0.59

 Gothic

-0.59

rero

-0.57

âķĲâķĲ

-0.57

 CLSID

-0.57

 isEnabled

-0.57

POSITIVE LOGITS

igg

1.24

uggets

1.23

imble

1.18

ought

1.13

anny

1.10

uke

1.10

ailing

1.10

umpy

1.10

usra

1.08

umerous

1.07

Activations Density 0.035%

the letter "n" followed by a digit, often associated with numerical values or identifiers

occurrences of the letter 'n'

No Comments

No Known Activations