INDEX

Explanations

statements expressing likelihood or expectation regarding events or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 apparently

-0.58

ริง

-0.44

 Apparently

-0.44

WEBPACK

-0.44

 evidently

-0.43

CP

-0.43

apparently

-0.43

Apparently

-0.43

такт

-0.43

!("{

-0.41

POSITIVE LOGITS

hood

1.08

دانشنامهٔ

0.92

usercontent

0.86

 AssemblyCulture

0.84

évaluateur

0.84

HOOD

0.83

 MainAxisSize

0.82

 hood

0.82

AnchorTagHelper

0.82

ItemBackground

0.81

Activations Density 0.090%

statements expressing likelihood or expectation regarding events or situations

No Comments

No Known Activations