INDEX

Explanations

characters used in string manipulations and operations

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

C++ or C# code snippets

np_acts-logits-general · gemini-2.0-flash

programming code

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 intptr

-1.02

Autoritní

-0.96

Hochspringen

-0.92

AndEndTag

-0.90

CodedInputStream

-0.89

 betweenstory

-0.84

ParallelGroup

-0.83

)");

-0.82

')")

-0.79

 ")");

-0.78

POSITIVE LOGITS

WriteLiteral

0.64

☝

0.53

"\

0.51

.=

0.51

Sto

0.50

Bout

0.49

 Bout

0.48

"\

0.47

fits

0.47

 rodin

0.46

Activations Density 0.032%

characters used in string manipulations and operations

C++ or C# code snippets

programming code

No Comments

No Known Activations