INDEX

Explanations

phrases indicating variations or categories of things

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.10

/***

-0.77

ExtendWith

-0.68

Fiche

-0.67

AllowUser

-0.67

RunWith

-0.67

hline

-0.67

Ша

-0.66

EqualsAnd

-0.66

///**

-0.64

POSITIVE LOGITS

 bandung

1.58

ftu

1.54

 lele

1.53

 milano

1.52

 napoli

1.50

 maroc

1.50

 nuoc

1.45

 thuy

1.45

 fatis

1.44

 haup

1.43

Activations Density 0.113%

phrases indicating variations or categories of things

No Comments

No Known Activations