INDEX

Explanations

names or terms related to specific individuals or organizations

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and places

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

 Lovecraft

-0.92

 Turtles

-0.90

 Wally

-0.85

OCD

-0.84

ãĤ´ãĥ³

-0.83

 Wonderland

-0.81

 Gravity

-0.81

 Grateful

-0.79

 Morty

-0.73

 Freak

-0.73

POSITIVE LOGITS

iya

1.17

awi

1.09

abi

1.08

ifa

1.07

arat

1.04

isan

1.02

hani

1.01

akh

1.00

Naj

1.00

usra

0.99

Activations Density 0.380%

names or terms related to specific individuals or organizations

proper nouns, particularly names and places

No Comments

No Known Activations