INDEX

Explanations

input and output function calls in programming

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

programming input operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DockStyle

-0.57

 ujednoznacz

-0.53

styleType

-0.50

writeFieldEnd

-0.49

 tartalomajánló

-0.47

%";

-0.47

LayoutPanel

-0.47

getMenuInflater

-0.46

TestingModule

-0.45

 createSlice

-0.45

POSITIVE LOGITS

lorette

0.48

findpost

0.42

 saisie

0.39

RTGC

0.39

charpe

0.38

Personendaten

0.38

 vägen

0.38

 réponses

0.38

anniversaire

0.38

quiagem

0.38

Activations Density 0.003%

input and output function calls in programming

programming input operations

No Comments

No Known Activations