INDEX

Explanations

references to complex relationships and interconnected concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 rằng

-0.57

hede

-0.52

argout

-0.51

them

-0.51

eningen

-0.51

how

-0.51

gate

-0.51

 hereof

-0.50

('.');

-0.49

ify

-0.49

POSITIVE LOGITS

 nobody

1.07

 many

1.03

 none

0.99

few

0.93

nobody

0.90

 neither

0.89

any

0.88

 muchos

0.87

 nessun

0.86

 anyone

0.85

Activations Density 0.210%

references to complex relationships and interconnected concepts

No Comments

No Known Activations