INDEX

Explanations

code-related logic and comparison functions

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

Comparisons and equality checks

np_acts-logits-general · gemini-2.0-flash

checking for equality using ==

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ContentAsync

-0.94

ConstraintMaker

-0.79

 dAtA

-0.69

 CreateTagHelper

-0.66

 disponibilités

-0.62

setVerticalGroup

-0.59

ScopeManager

-0.57

AndEndTag

-0.57

 SqlParameter

-0.55

 Winaray

-0.55

POSITIVE LOGITS

 compare

1.53

 comparing

1.51

compare

1.47

 comparison

1.45

 Compare

1.43

 compares

1.43

Compare

1.38

 Comparing

1.33

Comparing

1.32

 comparisons

1.31

Activations Density 0.299%

code-related logic and comparison functions

Comparisons and equality checks

checking for equality using ==

No Comments

No Known Activations