INDEX

Explanations

references to uncertainty or ambiguity in statements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

InjectAttribute

-0.96

 Qualquer

-0.87

 myſelf

-0.80

 ſche

-0.79

Personendaten

-0.78

 iſt

-0.78

 viewDidLoad

-0.74

Distribución

-0.74

География

-0.74

 itſelf

-0.74

POSITIVE LOGITS

 also

0.55

 something

0.51

 nothing

0.48

Nothing

0.45

 rien

0.44

far

0.44

no

0.43

 Nothing

0.42

もの

0.41

Activations Density 0.503%

references to uncertainty or ambiguity in statements

No Comments

No Known Activations