INDEX

Explanations

phrases and concepts related to theoretical frameworks and scientific methodology

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

preceding verbs like "treat", "give", "provide"

np_acts-logits-general · gemini-2.0-flash

to followed by verbs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

GraphicsUnit

-0.66

complexContent

-0.60

ThroughAttribute

-0.55

GOTREF

-0.54

 durer

-0.53

 laiss

-0.51

ViewFeatures

-0.51

 voud

-0.50

postsleuth

-0.50

 ControllerBase

-0.48

POSITIVE LOGITS

 obtain

0.75

 account

0.71

 derive

0.65

 extract

0.63

 model

0.61

 construct

0.61

 generate

0.60

 describe

0.60

 character

0.59

 infer

0.58

Activations Density 0.918%

phrases and concepts related to theoretical frameworks and scientific methodology

preceding verbs like "treat", "give", "provide"

to followed by verbs

No Comments

No Known Activations