INDEX

Explanations

references to speeches

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>

-3.02

ⓧ

-1.11

<?

-0.94

-0.90

/**

-0.86

/*

-0.79

/***

-0.67

fjspx

-0.64

/*++

-0.60

do

-0.57

POSITIVE LOGITS

 Minang

1.30

 bandung

1.29

 jawa

1.18

 speech

1.17

 thuy

1.16

 maroc

1.16

 signora

1.13

 soggior

1.12

 riva

1.12

 dises

1.11

Activations Density 0.040%

references to speeches

No Comments

No Known Activations