INDEX

Explanations

references to cells in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Plin

-0.81

 doInBackground

-0.75

 Réponses

-0.75

parseLong

-0.74

 izvē

-0.73

">)</

-0.73

SourceChecksum

-0.72

 valmis

-0.72

 SPIE

-0.71

‎‎

-0.71

POSITIVE LOGITS

 cell

2.40

cell

2.35

 cells

2.33

 CELL

2.33

 Cell

2.31

CELL

2.26

Cell

2.25

 Cells

2.19

Cells

2.17

cells

2.17

Activations Density 0.121%

references to cells in various contexts

No Comments

No Known Activations