INDEX

Explanations

connections and comparisons between different topics, particularly focusing on similarities and evaluations of effectiveness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

aarrggbb

-0.42

 kasarigan

-0.41

unhofer

-0.40

createTextNode

-0.40

InlineData

-0.40

ModelAdmin

-0.38

MLLoader

-0.38

PullParser

-0.38

IndentedString

-0.36

Datuak

-0.36

POSITIVE LOGITS

 similar

0.88

 similarities

0.77

 SIMILAR

0.75

 similaire

0.75

 Similar

0.74

 alike

0.73

 similares

0.72

similar

0.72

 same

0.71

Similar

0.70

Activations Density 0.671%

connections and comparisons between different topics, particularly focusing on similarities and evaluations of effectiveness

No Comments

No Known Activations