INDEX

Explanations

terms related to levels of quality or classification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

ThroughAttribute

-0.53

े

-0.50

참고

-0.48

enumi

-0.47

wiſe

-0.47

es

-0.45

 Irán

-0.45

 noël

-0.45

ToMove

-0.44

utuhkan

-0.44

POSITIVE LOGITS

arium

0.77

 medium

0.72

lium

0.71

 MAXIMUM

0.71

Medium

0.69

 MEDIUM

0.68

Maximum

0.67

rium

0.66

 Medium

0.66

um

0.66

Activations Density 0.284%

terms related to levels of quality or classification

No Comments

No Known Activations

terms related to levels of quality or classification

No Comments

No Known Activations