INDEX

Explanations

terms related to scientific methodology and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

身

-0.47

ítása

-0.41

被迫

-0.39

Ghe

-0.38

แล

-0.38

aman

-0.38

 Turner

-0.38

list

-0.38

BeforeClass

-0.38

ła

-0.37

POSITIVE LOGITS

 autorytatywna

0.97

 probabilities

0.94

 probability

0.89

 Савезне

0.87

 Probab

0.86

 utafitiHapana

0.85

TagMode

0.85

probability

0.84

raisemb

0.81

 likelihood

0.80

Activations Density 0.919%

terms related to scientific methodology and analysis

No Comments

No Known Activations