INDEX

Explanations

entities related to influence, specifically actors driving significant actions or outcomes

oai_token-act-pair · gpt-3.5-turbo

key entities and their roles in various contexts

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

ancies

-0.85

agate

-0.68

kay

-0.65

©¶æ

-0.65

thinkable

-0.62

Saharan

-0.61

arent

-0.61

 Remastered

-0.61

 staggered

-0.60

 gust

-0.60

POSITIVE LOGITS

 attracting

0.80

 GOODMAN

0.72

ä»£

0.71

 asset

0.71

 discipl

0.69

 extraord

0.68

ãĥĸ

0.68

PsyNetMessage

0.67

ipple

0.66

ARGET

0.66

Activations Density 0.246%

entities related to influence, specifically actors driving significant actions or outcomes

key entities and their roles in various contexts

No Comments

No Known Activations