INDEX

Explanations

programming function declarations and assertions in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

featureID

-1.05

GEBURTSDATUM

-0.92

Autoritní

-0.82

Vidite

-0.79

EDEFAULT

-0.79

aarrggbb

-0.72

principalColumn

-0.71

⟬

-0.70

RetentionPolicy

-0.70

 <<<<<<<<<<<<<<

-0.69

POSITIVE LOGITS

 respective

0.28

 jeweils

0.28

 perf

0.27

 Eins

0.26

 nhanh

0.26

Facades

0.25

 tiếp

0.25

Instantiate

0.24

 valida

0.24

 their

0.24

Activations Density 0.006%

programming function declarations and assertions in code

No Comments

No Known Activations