INDEX

Explanations

names that start with "Dri"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "driven" and its variations 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

anamo

-0.71

ä»£

-0.68

Osw

-0.67

ERAL

-0.65

çĦ

-0.65

 Patriot

-0.64

 Tosh

-0.64

 Augusta

-0.64

 procedural

-0.63

ivas

-0.63

POSITIVE LOGITS

zzle

1.26

zzy

1.18

Dri

1.15

Dri

1.13

ving

1.02

ven

0.98

ppings

0.96

dri

0.94

zz

0.92

cipled

0.91

Activations Density 0.009%

names that start with "Dri"

occurrences of the word "driven" and its variations in various contexts

No Comments

No Known Activations