INDEX

Explanations

statements expressing beliefs or opinions about integrity and assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ophora

-0.48

rains

-0.47

 Xuân

-0.47

 sabar

-0.47

vow

-0.46

⚭

-0.46

schöne

-0.46

zerw

-0.46

umumkan

-0.46

 doulou

-0.45

POSITIVE LOGITS

featureID

0.76

 كومونز

0.72

endphp

0.69

Personendaten

0.68

Geplaatst

0.67

BufferException

0.65

usercontent

0.63

 NSCoder

0.61

batore

0.60

 estekak

0.60

Activations Density 0.412%

statements expressing beliefs or opinions about integrity and assessments

No Comments

No Known Activations