INDEX

Explanations

specific identifiers or codes, likely related to classifications or numerical categorization

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>

-3.22

 виправивши

-1.11

MessageOf

-1.10

localctx

-1.07

/**

-1.03

Datuak

-1.02

tagHelperRunner

-1.01

contentLoaded

-1.00

/*

-1.00

 ddelweddau

-1.00

POSITIVE LOGITS

 affor

2.35

 unden

2.31

 depic

2.27

 impra

2.21

 ?...

2.17

 increa

2.14

 suscep

2.07

 stockholm

2.05

 compen

2.04

 unve

2.04

Activations Density 0.125%

specific identifiers or codes, likely related to classifications or numerical categorization

No Comments

No Known Activations