INDEX

Explanations

phrases related to justifications and conditions

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

 growing

-0.77

 Increasing

-0.76

 Growing

-0.75

 increasing

-0.74

 Changing

-0.74

 changing

-0.73

Growing

-0.73

growing

-0.71

Increasing

-0.71

Changing

-0.70

POSITIVE LOGITS

 saying

1.66

 stating

1.47

 noting

1.43

 suggesting

1.37

saying

1.35

 mentioning

1.35

 wondering

1.32

 describing

1.31

 asking

1.27

 thinking

1.26

Activations Density 0.493%

phrases related to justifications and conditions

No Comments

No Known Activations