INDEX

Explanations

phrases related to detailed analysis and evaluation

oai_token-act-pair · gpt-3.5-turbo

the word "of" 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ulla

-0.71

dayName

-0.68

ittees

-0.63

KK

-0.60

ertodd

-0.60

 trem

-0.59

 strugg

-0.59

 relied

-0.58

irs

-0.58

 rely

-0.57

POSITIVE LOGITS

 sorts

1.02

 course

0.95

tnc

0.71

 Excellence

0.69

Course

0.68

course

0.66

 rationality

0.66

how

0.63

issance

0.61

ãģĻ

0.60

Activations Density 0.244%

phrases related to detailed analysis and evaluation

the word "of" in various contexts

No Comments

No Known Activations