INDEX

Explanations

mentions of the word "Ace" followed by a numerical value ranging from 8 to 10

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Ace" 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

*/(

-0.77

soDeliveryDate

-0.77

FORMATION

-0.77

DERR

-0.72

isations

-0.70

asty

-0.69

chrom

-0.69

icity

-0.68

ATIONAL

-0.67

attribute

-0.66

POSITIVE LOGITS

Ace

1.08

Ĥª

0.81

 Hardware

0.80

reon

0.75

holders

0.75

ilon

0.74

assian

0.73

alus

0.72

 Patrol

0.70

idon

0.69

Activations Density 0.010%

mentions of the word "Ace" followed by a numerical value ranging from 8 to 10

mentions of the term "Ace" in various contexts

No Comments

No Known Activations