INDEX

Explanations

capital letter 'S'

oai_token-act-pair · gpt-3.5-turbo

the letter "S" 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EStream

-0.71

puter

-0.71

 techno

-0.69

 unrestricted

-0.68

catentry

-0.67

CPR

-0.64

 dealing

-0.62

 laureate

-0.61

 fret

-0.61

 unaccompanied

-0.60

POSITIVE LOGITS

ESSION

1.18

ustain

1.07

RS

1.06

igm

1.06

ixty

1.03

ufficient

1.03

igma

1.02

SA

1.02

SE

1.02

IX

1.01

Activations Density 0.081%

capital letter 'S'

the letter "S" in various contexts

No Comments

No Known Activations