INDEX

Explanations

game-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

SourceChecksum

-0.72

 Calvo

-0.58

躇

-0.57

 phosphorylation

-0.55

 phosphory

-0.51

 ddelweddau

-0.50

Beijinhos

-0.50

 Rouse

-0.48

})`

-0.47

 بتاريخ

-0.47

POSITIVE LOGITS

 suit

0.89

Ace

0.88

 clubs

0.88

 spades

0.87

 Clubs

0.86

 dealt

0.85

 Suit

0.84

ace

0.83

Ace

0.82

Clubs

0.81

Activations Density 0.232%

game-related terminology

No Comments

No Known Activations