INDEX

Explanations

dialogue related to discussions and interviews

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>

-2.23

<?

-0.91

ⓧ

-0.87

/**

-0.85

/*

-0.70

<?

-0.69

#![

-0.67

/***

-0.67

/****

-0.64

CopyWith

-0.59

POSITIVE LOGITS

 Minang

1.36

 maneu

1.27

 accla

1.22

 impra

1.17

 Czechos

1.09

 Keny

1.07

 practition

1.06

 Jambi

1.05

 Manufact

1.03

 Muhamma

1.03

Activations Density 0.385%

dialogue related to discussions and interviews

No Comments

No Known Activations