INDEX

Explanations

proper nouns related to people or entities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "roy"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

INESS

-0.76

pmwiki

-0.68

 Ammo

-0.65

 pity

-0.65

ogene

-0.65

iquid

-0.62

 Nadu

-0.60

awar

-0.59

 tending

-0.58

 amber

-0.58

POSITIVE LOGITS

alties

1.15

alty

1.03

ski

0.92

don

0.87

rence

0.86

din

0.85

doms

0.84

acy

0.84

dy

0.83

rer

0.81

Activations Density 0.015%

proper nouns related to people or entities

occurrences of the word "roy"

No Comments

No Known Activations