INDEX

Explanations

references to figures and data in scientific documents

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

Figure references (e.g., Fig. 1A)

np_acts-logits-general · gemini-2.0-flash

figure references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

----</

-0.70

LikeLiked

-0.60

+#+

-0.54

%]

-0.51

itattu

-0.48

CppCodeGen

-0.48

υσ

-0.47

equalTo

-0.46

]--;

-0.46

SetBool

-0.46

POSITIVE LOGITS

 depicts

0.65

 Wikimedijinoj

0.62

 scattata

0.62

 illustrates

0.61

 poffible

0.60

Panels

0.60

 displays

0.60

gráfica

0.59

below

0.58

зулта

0.58

Activations Density 0.713%

references to figures and data in scientific documents

Figure references (e.g., Fig. 1A)

figure references

No Comments

No Known Activations