INDEX

Explanations

print statements in code

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

print function calls

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

lo

-0.32

addVertex

-0.32

rig

-0.30

 []);

-0.30

sil

-0.30

 light

-0.30

(`/

-0.30

 زر

-0.29

吋

-0.27

 bike

-0.27

POSITIVE LOGITS

printStackTrace

0.77

+#+#

0.77

 AssemblyCulture

0.69

MemoryWarning

0.67

 للاسماء

0.67

SequentialGroup

0.66

MessageOf

0.65

WriteBarrier

0.63

#+#

0.63

requireNonNull

0.60

Activations Density 0.004%

print statements in code

print function calls

No Comments

No Known Activations

print statements in code

print function calls

No Comments

No Known Activations