INDEX

Explanations

code-related elements or structures, particularly function definitions or method calls

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

Code or programming-related text

np_acts-logits-general · gemini-2.0-flash

initialization and public declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

piew

-0.48

 raised

-0.48

ivez

-0.48

 directed

-0.47

AnchorStyles

-0.45

BorderFactory

-0.44

."""

-0.44

).

-0.44

 platform

-0.43

POSITIVE LOGITS

 الحره

1.01

InitVars

0.78

ThroughAttribute

0.76

DoubleQuotes

0.72

:✨

0.69

Népesség

0.63

 Wicidata

0.63

 صوتيه

0.61

skjaer

0.61

 للاسماء

0.60

Activations Density 0.247%

code-related elements or structures, particularly function definitions or method calls

Code or programming-related text

initialization and public declarations

No Comments

No Known Activations