INDEX

Explanations

references to research studies and evidence-based findings

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

Research/studies followed by "has", "have", or "may"

np_acts-logits-general · gemini-2.0-flash

research findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

EClass

-0.65

setContentView

-0.60

 OnInit

-0.58

 resourceCulture

-0.54

 eventdata

-0.51

ReusableCell

-0.51

 topic

-0.47

ngrx

-0.47

httphttps

-0.47

DoubleQuotes

-0.46

POSITIVE LOGITS

 indicates

0.68

 indicate

0.66

 INDIC

0.63

ParallelGroup

0.63

:][

0.62

 AspNetCore

0.61

indicates

0.60

 نشان

0.60

ismet

0.60

indicate

0.60

Activations Density 0.648%

references to research studies and evidence-based findings

Research/studies followed by "has", "have", or "may"

research findings

No Comments

No Known Activations