INDEX

Explanations

mentions of individuals with names containing "ero"

oai_token-act-pair · gpt-3.5-turbo

the word "ero" in various contexts

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

Ń·

-0.73

lv

-0.68

liam

-0.66

drawn

-0.65

Fif

-0.62

 Freed

-0.61

ividual

-0.60

 Berks

-0.60

hips

-0.60

ARDIS

-0.59

POSITIVE LOGITS

ero

1.10

edia

1.06

eli

0.93

osa

0.89

oma

0.84

oya

0.83

ose

0.82

quin

0.82

cephal

0.81

isine

0.81

Activations Density 0.008%

mentions of individuals with names containing "ero"

the word "ero" in various contexts

No Comments

No Known Activations