INDEX

Explanations

instances where someone is attempting or striving to achieve something

oai_token-act-pair · gpt-3.5-turbo

phrases related to gaining support or involvement 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

cember

-0.64

Downloadha

-0.59

 multiplied

-0.55

 averaged

-0.55

emed

-0.55

[-

-0.53

 consisted

-0.53

 tends

-0.52

 exclaimed

-0.52

 rotated

-0.51

POSITIVE LOGITS

 ASAP

0.64

 someday

0.63

 rethink

0.59

 urgently

0.59

ordable

0.58

 faire

0.58

 profitability

0.57

 financially

0.56

 grassroots

0.56

Brexit

0.56

Activations Density 0.918%

instances where someone is attempting or striving to achieve something

phrases related to gaining support or involvement in various contexts

No Comments

No Known Activations