INDEX

Explanations

occurrences of the word "on."

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>

-2.48

ⓧ

-0.97

<?

-0.71

/**

-0.67

uxxxx

-0.58

 viewWillAppear

-0.58

RegressionTest

-0.58

get

-0.57

 awakeFromNib

-0.57

ViewFeatures

-0.57

POSITIVE LOGITS

 maneu

1.45

 accla

1.39

 Keny

1.31

Juf

1.28

 délib

1.25

 Ferdin

1.24

 épu

1.21

 soulign

1.20

 habile

1.20

 véhic

1.19

Activations Density 0.203%

occurrences of the word "on."

No Comments

No Known Activations