INDEX

Explanations

elements related to programming structures and their parameters

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

Code-related terms or code

np_acts-logits-general · gemini-2.0-flash

function definitions or lambda calls

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

يكب

-0.56

TableHead

-0.55

jsdelivr

-0.55

ranos

-0.47

-0.46

sek

-0.46

wys

-0.45

ADES

-0.45

stere

-0.45

Beg

-0.44

POSITIVE LOGITS

 فريبيس

0.89

RenderAtEndOf

0.80

formik

0.77

 purpoſe

0.76

 pleaſure

0.74

oredCriteria

0.73

 كومونز

0.73

 그리고

0.73

+#+#

0.72

 myſelf

0.71

Activations Density 0.478%

elements related to programming structures and their parameters

Code-related terms or code

function definitions or lambda calls

No Comments

No Known Activations