INDEX

Explanations

references to programming structures and function definitions

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

AIPS task names

np_acts-logits-general · gemini-2.0-flash

task command names

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 security

-0.53

 business

-0.51

 Security

-0.47

naphthal

-0.45

Parab

-0.45

 garden

-0.45

 Route

-0.43

Bot

-0.43

Oscill

-0.43

 route

-0.43

POSITIVE LOGITS

 propOrder

0.80

Kariera

0.74

SequentialGroup

0.72

SBATCH

0.72

omeness

0.71

出版年

0.69

 jsPsych

0.68

Биография

0.67

 Walkover

0.64

 rhestr

0.64

Activations Density 1.443%

references to programming structures and function definitions

AIPS task names

task command names

No Comments

No Known Activations