INDEX

Explanations

programming constructs and formatting related to data handling

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

Within brackets, after "Fig" or "fig"

np_acts-logits-general · gemini-2.0-flash

Stepper constructor calls

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

!_

-0.72

TagMode

-0.53

gow

-0.52

${{

-0.52

[%

-0.52

_{-\

-0.51

 ſen

-0.51

 ويكيميديا

-0.50

[\

-0.50

_{{\

-0.50

POSITIVE LOGITS

1.49

0.70

AutoField

0.60

<>(

0.59

mergeFrom

0.58

WithMany

0.58

Jeografia

0.58

nonatomic

0.57

()

0.57

.(

0.57

Activations Density 0.805%

programming constructs and formatting related to data handling

Within brackets, after "Fig" or "fig"

Stepper constructor calls

No Comments

No Known Activations