INDEX

Explanations

words related to data analysis and technical terms

oai_token-act-pair · gpt-3.5-turbo

the conjunction "and" in various contexts

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

NULL

-0.67

 Vaugh

-0.64

 incent

-0.62

anu

-0.62

legate

-0.61

bub

-0.59

[*

-0.58

avorite

-0.58

abee

-0.57

 disadvant

-0.55

POSITIVE LOGITS

 consequently

0.64

rogens

0.64

 then

0.62

rogen

0.62

 therefore

0.62

0.59

 possibly

0.59

 thus

0.58

 thence

0.55

 hence

0.53

Activations Density 0.342%

words related to data analysis and technical terms

the conjunction "and" in various contexts

No Comments

No Known Activations