INDEX

Explanations

references to geographical locations and positional phrases

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

 Normdatei

-0.55

withIdentifier

-0.54

pdp

-0.52

ascending

-0.49

halt

-0.48

TestTools

-0.48

روز

-0.47

ONCE

-0.46

 saken

-0.46

InstrumentedTest

-0.46

POSITIVE LOGITS

 beginnetje

0.68

MigrationBuilder

0.64

ervlak

0.64

off

0.64

icksburg

0.63

ThroughAttribute

0.60

sizeCache

0.59

/*

0.58

sanity

0.58

newBuilder

0.57

Activations Density 0.079%

references to geographical locations and positional phrases

No Comments

No Known Activations