INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.55

ⓧ

-1.14

/**

-1.10

<?

-1.10

-1.04

 disbur

-0.78

 endow

-0.77

/***

-0.76

 inaugurate

-0.76

<?

-0.75

POSITIVE LOGITS

 saar

1.34

 lele

1.15

 seksi

1.14

 jawa

1.11

 Minang

1.09

 Karang

1.08

 maksi

1.08

 lemp

1.08

 riva

1.08

 bandung

1.07

Activations Density 0.071%

No Comments

No Known Activations