INDEX

Explanations

nicknames or alternate names for people

oai_token-act-pair · gpt-3.5-turbo

names and their corresponding nicknames or aliases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 replication

-0.77

 universities

-0.76

 advancement

-0.74

 explor

-0.74

 libraries

-0.72

 departments

-0.72

iments

-0.70

 databases

-0.69

 exclusion

-0.68

ications

-0.68

POSITIVE LOGITS

 Mister

1.04

Sno

0.99

 Uncle

0.98

 Johnny

0.98

 Sonny

0.96

 Captain

0.95

 Sergeant

0.94

Johnny

0.93

 Freddie

0.91

 Willie

0.90

Activations Density 0.244%

nicknames or alternate names for people

names and their corresponding nicknames or aliases

No Comments

No Known Activations