INDEX

Explanations

keywords related to technology and settings

oai_token-act-pair · gpt-3.5-turbo

key terms related to classification and categorization 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

terday

-1.04

etheless

-0.89

itably

-0.87

anwhile

-0.86

 compr

-0.71

gomery

-0.69

 vain

-0.69

iannopoulos

-0.68

 youthful

-0.68

 republican

-0.67

POSITIVE LOGITS

 Mode

1.10

 Manager

1.07

 Selection

1.05

 Breaker

1.03

Ship

1.03

 Points

1.02

 Room

1.01

 Meter

1.01

Pass

1.01

 Builder

1.01

Activations Density 0.406%

keywords related to technology and settings

key terms related to classification and categorization in various contexts

No Comments

No Known Activations