INDEX

Explanations

popular things or activities within various contexts

oai_token-act-pair · gpt-3.5-turbo

instances of popularity or common acceptance among specific groups or categories

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

ratulations

-0.72

oulos

-0.69

arations

-0.67

 detachment

-0.67

ument

-0.65

ensing

-0.64

ifax

-0.62

arching

-0.62

igible

-0.62

 Canaver

-0.61

POSITIVE LOGITS

 Occupations

0.90

ORPG

0.87

aceae

0.86

å§«

0.86

 à¨

0.77

Tea

0.72

Used

0.72

 Used

0.71

Synopsis

0.70

 nowadays

0.70

Activations Density 0.279%

popular things or activities within various contexts

instances of popularity or common acceptance among specific groups or categories

No Comments

No Known Activations