INDEX

Explanations

formatting elements and structural markers in text

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

Followed by a symbol or number

np_acts-logits-general · gemini-2.0-flash

biological terms 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 @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

setVerticalGroup

-0.73

 وتسجيلات

-0.68

 Paglinawan

-0.67

tvguidetime

-0.61

AccessorTable

-0.61

RegressionTest

-0.59

CloseOperation

-0.59

//

-0.58



-0.56

POSITIVE LOGITS

<h4>

2.05

</h4>

1.47

1.13

<h5>

0.94

"/>

0.89

↵↵↵↵

0.88

subsubsection

0.84

。

0.82

</blockquote>

0.78

```

0.76

Activations Density 0.051%

formatting elements and structural markers in text

Followed by a symbol or number

biological terms and code snippets

No Comments

No Known Activations