INDEX

Explanations

instances of punctuation or dash-like symbols indicating interruptions or breaks in text

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

Text after a dash or em dash

np_acts-logits-general · gemini-2.0-flash

followed by explanations

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

دانشنامهٔ

-0.82

UnsafeEnabled

-0.79

bootstrapcdn

-0.76

ponses

-0.73

 nakalista

-0.72

GHI

-0.71

Filmographie

-0.70

SharedDtor

-0.70

 ExecuteAsync

-0.69

 propOrder

-0.68

POSITIVE LOGITS

––––

1.40

––

1.08

–

1.05

–

0.98

0.95

.–

0.93

0.91

)–

0.90

്‍

0.85

,–

0.83

Activations Density 0.223%

instances of punctuation or dash-like symbols indicating interruptions or breaks in text

Text after a dash or em dash

followed by explanations

No Comments

No Known Activations