INDEX

Explanations

organizations or entities represented by the term "CA"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "CA" related to various organizations or contexts

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

lings

-0.90

schild

-0.78

minster

-0.73

lihood

-0.71

flows

-0.70

geist

-0.70

ãĥĦ

-0.68

 athlet

-0.68

ipeg

-0.68

eering

-0.67

POSITIVE LOGITS

UTION

1.11

esar

1.03

IRO

1.03

USE

1.01

FE

0.94

ULT

0.92

xon

0.91

CA

0.89

KE

0.88

IR

0.86

Activations Density 0.007%

organizations or entities represented by the term "CA"

occurrences of the abbreviation "CA" related to various organizations or contexts

No Comments

No Known Activations