INDEX

Explanations

terms related to disruption or alteration in a variety of contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.40.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

ized

-1.27

ated

-1.20

ется

-0.93

った

-0.86

anteed

-0.84

した

-0.81

ured

-0.75

tituted

-0.75

ATED

-0.68

ulated

-0.67

POSITIVE LOGITS

Ƚ

0.49

Ed

0.45

ting

0.40

TypedDataSet

0.40

tituting

0.40

ening

0.39

XtraGrid

0.38

Ed

0.38

TING

0.38

Hozzáférés

0.36

Activations Density 0.469%

terms related to disruption or alteration in a variety of contexts

No Comments

No Known Activations

terms related to disruption or alteration in a variety of contexts

No Comments

No Known Activations