INDEX

Explanations

occurrences of scientific terms and data related to mutations and experimental results

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

Text after commas

np_acts-logits-general · gemini-2.0-flash

specific assertions

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

 however

-0.72

However

-0.62

 However

-0.60

however

-0.59

-0.58

-0.56

 though

-0.54

-0.52

 usual

-0.50

los

-0.49

POSITIVE LOGITS

ScopeManager

1.22

 GenerationType

1.00

extAlignment

0.91

 TextInputType

0.88

ImageContext

0.88

RectangleBorder

0.87

DockStyle

0.86

astify

0.82

InputBorder

0.81

LEncoder

0.80

Activations Density 0.952%

occurrences of scientific terms and data related to mutations and experimental results

Text after commas

specific assertions

No Comments

No Known Activations