INDEX

Explanations

mentions of groups or entities as a single unit or entity

oai_token-act-pair · gpt-3.5-turbo

phrases that describe groups or collectives using the term "a" to indicate unity or whole

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

pages

-0.72

Dutch

-0.71

Access

-0.70

andon

-0.70

Elect

-0.69

bots

-0.67

âĿ

-0.67

mares

-0.67

events

-0.66

Attach

-0.66

POSITIVE LOGITS

 result

1.28

 consequence

1.06

 standalone

0.98

 reminder

0.95

 spectator

0.91

 member

0.87

 guideline

0.86

 catalyst

0.85

 matter

0.85

 prerequisite

0.85

Activations Density 0.108%

mentions of groups or entities as a single unit or entity

phrases that describe groups or collectives using the term "a" to indicate unity or whole

No Comments

No Known Activations