INDEX

Explanations

phrases that indicate time or sequential events, particularly those using the word "next."

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>

-2.27

/***

-0.77

/**

-0.67

<?

-0.64

emplace

-0.62

-0.61

///**

-0.59

declare

-0.58

 mobilize

-0.58

ⓧ

-0.58

POSITIVE LOGITS

 vespa

1.11

 chrysler

1.11

 mitsubishi

1.08

 opport

1.08

 imposs

1.08

 pican

1.07

 peugeot

1.07

 accla

1.07

 suspic

1.06

 bosch

1.05

Activations Density 0.060%

phrases that indicate time or sequential events, particularly those using the word "next."

No Comments

No Known Activations