INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

references to significant titles or names, particularly in literature, movies, or projects

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

ãĥ£

-0.65

¶ħ

-0.64

ctica

-0.63

ãĤ°

-0.62

 photoc

-0.60

DOI

-0.56

meg

-0.55

 grandma

-0.54

Ñı

-0.54

 compr

-0.54

POSITIVE LOGITS

ingham

0.68

 Ones

0.64

enson

0.62

pedia

0.61

later

0.61

 Labs

0.61

 Jinn

0.59

 Timbers

0.58

 Field

0.58

 Lodge

0.58

Activations Density 0.392%

proper nouns

references to significant titles or names, particularly in literature, movies, or projects

No Comments

No Known Activations