INDEX

Explanations

specific nouns or phrases related to various topics, potentially keywords for further detailed analysis

oai_token-act-pair · gpt-3.5-turbo

specific nouns and proper names related to various topics or entities

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

idth

-0.60

 Katy

-0.58

arij

-0.58

Mew

-0.57

lap

-0.56

WW

-0.55

ync

-0.54

 Nich

-0.54

 Kang

-0.53

 Judd

-0.51

POSITIVE LOGITS

 itself

0.81

 altogether

0.69

 herself

0.67

selves

0.64

alian

0.61

âĢ²

0.61

 Leilan

0.60

 afterwards

0.59

 himself

0.58

 afterward

0.58

Activations Density 0.689%

specific nouns or phrases related to various topics, potentially keywords for further detailed analysis

specific nouns and proper names related to various topics or entities

No Comments

No Known Activations