INDEX

Explanations

descriptions of distinct categories or classifications within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 maș

-0.42

 conseille

-0.41

 recomiendo

-0.41

iss

-0.40

nî

-0.40

cor

-0.40

 préf

-0.39

kú

-0.37

si

-0.37

sim

-0.37

POSITIVE LOGITS

AndEndTag

1.10

PreExecute

0.93

SequentialGroup

0.88

FunctionFlags

0.88

WriteTagHelper

0.84

StreetMap

0.83

tagext

0.83

 оригіналу

0.83

 AssemblyCulture

0.81

readystatechange

0.81

Activations Density 0.484%

descriptions of distinct categories or classifications within a context

No Comments

No Known Activations