INDEX

Explanations

words and phrases that suggest a description or perception of appearance

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate appearances or perceptions of objects or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

omics

-0.76

ients

-0.74

cest

-0.68

 seldom

-0.68

indust

-0.67

anwhile

-0.67

è¦ļéĨĴ

-0.67

limits

-0.66

ickr

-0.66

Events

-0.65

POSITIVE LOGITS

 imitate

0.89

 resemble

0.89

 condone

0.87

be

0.83

 resemblance

0.81

 belong

0.79

 simulate

0.79

 violate

0.79

 originate

0.79

 confirm

0.76

Activations Density 0.074%

words and phrases that suggest a description or perception of appearance

phrases that indicate appearances or perceptions of objects or situations

No Comments

No Known Activations