INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

names of people, places, or brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 respectively

-0.76

 thereto

-0.61

 fame

-0.60

 attest

-0.60

 otherwise

-0.59

 prevailing

-0.56

 precursor

-0.56

ãģ¾

-0.54

 kindred

-0.53

 privileged

-0.53

POSITIVE LOGITS

 Profile

0.71

asma

0.68

ertodd

0.66

enza

0.65

ius

0.63

endum

0.62

anyahu

0.61

iott

0.61

 Functions

0.61

arij

0.60

Activations Density 1.644%

proper nouns

names of people, places, or brands

No Comments

No Known Activations