INDEX

Explanations

phrases related to efforts aiming to achieve a specific goal or result

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "bring" 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

 msec

-0.71

 fixme

-0.68

 Invasion

-0.67

 preferring

-0.62

 wander

-0.61

 suffers

-0.61

 Inher

-0.61

-0.59

 boasting

-0.57

 nervously

-0.57

POSITIVE LOGITS

rid

0.83

uate

0.75

igate

0.70

aun

0.67

 forth

0.65

rave

0.64

AW

0.64

 meaningful

0.63

engers

0.63

TER

0.63

Activations Density 0.245%

phrases related to efforts aiming to achieve a specific goal or result

occurrences of the word "bring" in various contexts

No Comments

No Known Activations