INDEX

Explanations

words related to current events or news

oai_token-act-pair · gpt-3.5-turbo

terms related to various aspects of location, events, and media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

soever

-0.60

Compat

-0.57

thood

-0.57

Cola

-0.55

Eva

-0.54

 Disorder

-0.54

edIn

-0.54

è¡

-0.53

åĮ

-0.53

 Worth

-0.52

POSITIVE LOGITS

iest

1.13

liest

1.06

ultimate

0.90

same

0.79

 portion

0.77

osphere

0.71

est

0.67

 aisle

0.66

most

0.66

hest

0.66

Activations Density 0.810%

words related to current events or news

terms related to various aspects of location, events, and media

No Comments

No Known Activations