INDEX

Explanations

phrases related to financial transactions

oai_token-act-pair · gpt-3.5-turbo

references to monetary compensation or remuneration

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

------

-0.81

ãĤ¦

-0.78

-----

-0.77

ember

-0.74

Dak

-0.73

Ou

-0.68

 Scotia

-0.67

 Nether

-0.67

 Liberia

-0.66

è¦ļéĨĴ

-0.66

POSITIVE LOGITS

checks

0.86

oshenko

0.83

 pays

0.82

ordable

0.82

cale

0.82

chwitz

0.82

iotics

0.79

htaking

0.79

heet

0.79

inois

0.78

Activations Density 0.005%

phrases related to financial transactions

references to monetary compensation or remuneration

No Comments

No Known Activations