INDEX

Explanations

elements related to HTTP response statuses and errors

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

Mathematical symbols and equations

np_acts-logits-general · gemini-2.0-flash

following '4' or ')'

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

↵↵

-0.94

↵

-0.88

-0.69

</h3>

-0.67

-0.63

-0.62

-0.61

 Post

-0.60

-0.59

-0.58

POSITIVE LOGITS

 itſelf

1.09

 myſelf

1.09

 doubtnut

1.00

 ་་

0.99

 Monfieur

0.98

 depositphotos

0.96

 pleaſure

0.95

 iſt

0.94

 ſind

0.93

uſ

0.92

Activations Density 0.167%

elements related to HTTP response statuses and errors

Mathematical symbols and equations

following '4' or ')'

No Comments

No Known Activations