INDEX

Explanations

excessive repetitions of the term "much" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 target

-0.54

 invol

-0.49

 folos

-0.49

Història

-0.47

bootstrapcdn

-0.46

If

-0.46

iry

-0.46

рию

-0.46

Non

-0.45

交

-0.44

POSITIVE LOGITS

 another

0.88

 multiple

0.82

another

0.74

]='\

0.73

NUMX

0.73

 betweenstory

0.71

)"),

0.71

 numerous

0.70

EDEFAULT

0.70

 findViewById

0.69

Activations Density 0.246%

excessive repetitions of the term "much" in various contexts

No Comments

No Known Activations