INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

names or references to specific individuals and their actions

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

uces

-0.69

itled

-0.68

ptive

-0.68

Ľ

-0.67

ublished

-0.66

remlin

-0.65

manac

-0.64

obook

-0.64

ark

-0.63

ract

-0.63

POSITIVE LOGITS

etc

2.00

etc

1.85

whatever

1.60

 blah

1.42

 whatever

1.41

ect

1.23

anything

1.07

âĢ¦)

1.07

...)

1.01

 yeah

0.99

Activations Density 0.276%

proper nouns

names or references to specific individuals and their actions

No Comments

No Known Activations