INDEX

Explanations

proper nouns, especially those relating to locations and entities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.53

ⓧ

-1.08

/**

-1.06

<?

-0.96

/*

-0.95

-0.94

#![

-0.78

<?

-0.76

rungsseite

-0.74

 <>",

-0.72

POSITIVE LOGITS

 keramik

1.14

 lele

1.14

 kafe

1.06

 teras

1.04

 maksi

1.04

 kristal

1.03

 silikon

1.02

 optik

1.01

 kasa

1.00

 seksi

1.00

Activations Density 0.458%

proper nouns, especially those relating to locations and entities

No Comments

No Known Activations