INDEX

Explanations

words related to the concept of something that is never-ending or impossible to stop

oai_token-act-pair · gpt-3.5-turbo

words related to inexorable or unstoppable forces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

istically

-0.95

eering

-0.75

istic

-0.72

isers

-0.72

ographically

-0.71

izing

-0.71

ists

-0.70

imer

-0.68

otonin

-0.67

ize

-0.65

POSITIVE LOGITS

natureconservancy

0.79

ility

0.79

acious

0.73

contin

0.72

acity

0.72

 Bland

0.69

aciously

0.69

nant

0.69

illation

0.68

ENCE

0.67

Activations Density 0.048%

words related to the concept of something that is never-ending or impossible to stop

words related to inexorable or unstoppable forces

No Comments

No Known Activations