INDEX

Explanations

button classes or identifiers used in a code context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Personendaten

-0.84

SourceChecksum

-0.64

richTextPanel

-0.54

tahui

-0.54

 &___

-0.53

 kasarigan

-0.51

lavia

-0.50

FunctionFlags

-0.48

 endblock

-0.48

="/">

-0.48

POSITIVE LOGITS

SBATCH

0.79

 BorderRadius

0.77

 CURLOPT

0.73

 FetchType

0.70

 navbar

0.68

 Offisielt

0.67

󠁧

0.64

 glyphicon

0.61

oczes

0.61

 незавершена

0.61

Activations Density 0.035%

button classes or identifiers used in a code context

No Comments

No Known Activations