INDEX

Explanations

articles and descriptors indicating significance or emphasis in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 gynhyrchwyd

-0.91

+#+#

-0.78

principalColumn

-0.75

 AssemblyCulture

-0.73

 المعيارى

-0.71

 nakalista

-0.71

 विश्वसनीयता

-0.70

RTEX

-0.69

wieś

-0.67



-0.67

POSITIVE LOGITS

 recent

0.82

 further

0.78

 majority

0.76

 perusal

0.70

 good

0.69

 prerequisite

0.68

key

0.68

 spokesman

0.67

 quick

0.67

recent

0.67

Activations Density 0.447%

articles and descriptors indicating significance or emphasis in scientific contexts

No Comments

No Known Activations