INDEX

Explanations

references to entities or compounds in various contexts

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>

-2.20

 opzioni

-0.99

 applicazioni

-0.93

 jette

-0.90

 mantenga

-0.89

 versioni

-0.84

 encuentre

-0.83

 considère

-0.81

 reconnaît

-0.81

 conseguenze

-0.78

POSITIVE LOGITS

 accla

1.55

 uncin

1.45

 maneu

1.44

 unce

1.42

 socie

1.42

 affor

1.42

 conspic

1.41

 juven

1.40

 reluct

1.36

 unve

1.35

Activations Density 0.655%

references to entities or compounds in various contexts

No Comments

No Known Activations