INDEX

Explanations

correlations between quantities and their effects or attributes within a context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

alnız

-0.57

LookAnd

-0.53

 hadn

-0.52

//*[@

-0.50

dfunding

-0.50

zig

-0.49

 betweenstory

-0.49

wasn

-0.49

 Changed

-0.48

zupeł

-0.47

POSITIVE LOGITS

 càng

1.08

 desto

1.00

 semakin

0.97

越是

0.90

越好

0.89

越

0.87

越

0.85

越高

0.84

越多

0.83

ほど

0.81

Activations Density 0.400%

correlations between quantities and their effects or attributes within a context

No Comments

No Known Activations