INDEX

Explanations

phrases related to technical systems or products

oai_token-act-pair · gpt-3.5-turbo

references to various systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 diamonds

-0.71

 bapt

-0.68

hur

-0.66

forth

-0.65

fet

-0.64

ulton

-0.64

 bust

-0.62

 delight

-0.62

flame

-0.62

 Harley

-0.61

POSITIVE LOGITS

 System

3.72

System

2.61

 system

2.36

 SYSTEM

2.34

system

2.32

 Systems

2.26

 systems

1.84

ystem

1.37

Sys

1.33

 Program

1.19

Activations Density 0.017%

phrases related to technical systems or products

references to various systems

No Comments

No Known Activations