INDEX

Explanations

mentions of legal or official titles such as "Magistrate" or "Mag"

oai_token-act-pair · gpt-3.5-turbo

mentions of "Magistrate."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãģį

-1.04

OPLE

-0.95

éĹĺ

-0.75

INGTON

-0.68

ãĤĤ

-0.68

 Rockefeller

-0.68

 Hurricanes

-0.67

kHz

-0.65

 Siem

-0.65

ãģ¯

-0.65

POSITIVE LOGITS

istrate

1.47

istrates

1.39

nesium

1.32

ikarp

1.31

azines

1.28

netic

1.21

ento

1.07

pie

1.06

enta

1.04

lia

1.01

Activations Density 0.015%

mentions of legal or official titles such as "Magistrate" or "Mag"

mentions of "Magistrate."

No Comments

No Known Activations