INDEX

Explanations

names of individuals, possibly with specific characteristics or professions

oai_token-act-pair · gpt-3.5-turbo

names and references related to specific individuals, particularly the name "Daly."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

pocket

-0.73

Kin

-0.73

assium

-0.69

encers

-0.66

achusetts

-0.66

achus

-0.66

Ak

-0.65

berman

-0.63

belt

-0.62

Ak

-0.62

POSITIVE LOGITS

mares

1.03

 Daly

1.01

mare

0.77

onge

0.74

angelo

0.69

pine

0.67

uci

0.67

ously

0.67

osal

0.66

ucci

0.65

Activations Density 0.025%

names of individuals, possibly with specific characteristics or professions

names and references related to specific individuals, particularly the name "Daly."

No Comments

No Known Activations