INDEX

Explanations

words related to standard or usual things, particularly when used within a comparison or describing something

oai_token-act-pair · gpt-3.5-turbo

the concept of "typical" as it relates to various subjects or situations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Starship

-0.77

heed

-0.76

nuts

-0.72

hips

-0.70

hani

-0.69

ole

-0.66

robe

-0.65

aska

-0.63

hung

-0.63

han

-0.62

POSITIVE LOGITS

typ

0.77

 embodiments

0.75

 deviations

0.75

 occurrences

0.71

CRIPTION

0.71

 deviation

0.70

 typical

0.70

 depictions

0.69

uously

0.67

 weekday

0.66

Activations Density 0.016%

words related to standard or usual things, particularly when used within a comparison or describing something

the concept of "typical" as it relates to various subjects or situations

No Comments

No Known Activations