INDEX

Explanations

segments of code related to function definitions and method calls

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

Mathematical or code-related symbols and expressions

np_acts-logits-general · gemini-2.0-flash

build trust and technical terms

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

 CreateTagHelper

-0.63

Rohy

-0.59

tvguidetime

-0.58

%%

-0.55

ladolid

-0.51

 mukana

-0.51

 Italijani

-0.50

varing

-0.49

rindo

-0.49

daction

-0.48

POSITIVE LOGITS

setVerticalGroup

0.68

sizeCache

0.64

انجليز

0.59

iastes

0.57

Referanser

0.57

Архівовано

0.56

 Վերցված

0.56

</caption>

0.56

protoc

0.56

 consultato

0.56

Activations Density 0.044%

segments of code related to function definitions and method calls

Mathematical or code-related symbols and expressions

build trust and technical terms

No Comments

No Known Activations