INDEX

Explanations

details related to news broadcasting and television programs

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

ordinaire

-0.48

raszam

-0.48

EDEFAULT

-0.47

houding

-0.45

znym

-0.45

Bref

-0.44

DDD

-0.44

Tracce

-0.42

__;

-0.42

je

-0.42

POSITIVE LOGITS

 ſta

0.72

 ſtate

0.68

 opérateur

0.66

 ftate

0.66

 raiſ

0.66

 Majefty

0.66

ItemLayout

0.65

">${

0.65

########.

0.64

 ſon

0.63

Activations Density 0.070%

details related to news broadcasting and television programs

No Comments

No Known Activations