INDEX

Explanations

references to change or transitions in situations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Code snippets or mathematical expressions

np_acts-logits-general · gemini-2.0-flash

mathematical expressions and code snippets

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

…

-0.89

 ….

-0.83

 …)

-0.82

՚

-0.81

¦

-0.77

…~

-0.77

 …………

-0.75

 …”

-0.75

 ब्रेकडाउन

-0.73

 виправивши

-0.72

POSITIVE LOGITS

--

0.71

...

0.70

0.66

--

0.63

 postIndex

0.60

'--

0.58

</h6>

0.57

....

0.57

'''

0.56

---

0.56

Activations Density 0.352%

references to change or transitions in situations

Code snippets or mathematical expressions

mathematical expressions and code snippets

No Comments

No Known Activations