INDEX

Explanations

adjectives and nouns related to negation or absence

oai_token-act-pair · gpt-3.5-turbo

phrases or terms that indicate negation or lack of attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Tycoon

-0.79

 edges

-0.71

 layers

-0.69

 cohorts

-0.67

 Born

-0.67

 younger

-0.67

 creators

-0.66

 heights

-0.66

 rooft

-0.65

 backgrounds

-0.65

POSITIVE LOGITS

functional

1.22

existent

1.16

starter

1.13

standard

1.07

threatening

1.03

responsive

1.02

answer

1.00

issue

1.00

competitive

0.97

productive

0.96

Activations Density 0.098%

adjectives and nouns related to negation or absence

phrases or terms that indicate negation or lack of attributes

No Comments

No Known Activations