INDEX

Explanations

non-English words or phrases that indicate interaction or actions involving a player or participant

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ิด

-0.49

 lửa

-0.43

 rapport

-0.43

ungsbedingungen

-0.42

IGR

-0.42

staan

-0.41

 داریم

-0.41

 هستیم

-0.41

('.'

-0.41

itati

-0.41

POSITIVE LOGITS

principalColumn

1.05

MigrationBuilder

0.92

+#+#

0.84

sizeCache

0.83

'{@

0.82

 виправивши

0.82

makeConstraints

0.82

tableFuture

0.79

 estekak

0.79

 himself

0.78

Activations Density 0.594%

non-English words or phrases that indicate interaction or actions involving a player or participant

No Comments

No Known Activations