INDEX

Explanations

terms related to processes or actions in various contexts

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

words ending in ation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

NSError

-0.59

bootstrapcdn

-0.54

glTexCoord

-0.54

ᅠ

-0.47

]];

-0.47

]++;

-0.45

ningarna

-0.44

unhofer

-0.44

SequentialGroup

-0.44

rawQuery

-0.44

POSITIVE LOGITS

хьтан

0.45

原始内容存档于

0.42

Tikang

0.41

 Audiodateien

0.35

sidemargin

0.35

display

0.35

synthesize

0.34

گن

0.34

 Início

0.34

 officielle

0.33

Activations Density 0.050%

terms related to processes or actions in various contexts

words ending in ation

No Comments

No Known Activations