INDEX

Explanations

negative descriptors or phrases related to social critiques and personal experiences

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>

-2.05

//---

-0.64

 incarcer

-0.58

ManyToMany

-0.57

displayquote

-0.55

testng

-0.55

//<

-0.54

/***

-0.52

 continue

-0.52

انجليز

-0.51

POSITIVE LOGITS

 churrasco

1.12

 pimiento

1.05

 chèvre

1.04

 scatt

1.02

 sappi

1.00

 LIRE

0.99

 papà

0.98

 Áng

0.98

 firebaseConfig

0.97

 tramont

0.97

Activations Density 0.368%

negative descriptors or phrases related to social critiques and personal experiences

No Comments

No Known Activations