INDEX

Explanations

references to familial relationships

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

Followed by "user" or relating to information

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

—”

-0.48

—

-0.45

?!?

-0.44

 interpretive

-0.40

 Shaksp

-0.40

uesday

-0.39

jé

-0.39

，”

-0.38

 gleaned

-0.38

℠

-0.38

POSITIVE LOGITS

 equipments

0.84

 hence

0.82

 ModelExpression

0.74

 irrespective

0.72

 Hence

0.72

 which

0.66

 namely

0.65

 noOf

0.65

 till

0.63

 whereas

0.61

Activations Density 1.057%

references to familial relationships

Followed by "user" or relating to information

No Comments

No Known Activations