INDEX

Explanations

terms related to resistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

gameserver

-0.70

paravant

-0.65

 magasiner

-0.62

LookAnd

-0.61

 BoxFit

-0.58

Schedulers

-0.58

 didat

-0.58

 mẽ

-0.57

 تانيه

-0.55

!("{}",

-0.55

POSITIVE LOGITS

 tolerance

1.77

 resistance

1.75

 resilience

1.62

 Resistance

1.55

 Tolerance

1.52

tolerance

1.47

Resistance

1.46

resistance

1.42

 Resilience

1.41

Tolerance

1.37

Activations Density 0.119%

terms related to resistance

No Comments

No Known Activations