INDEX

Explanations

references to homework assignments and related tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ehe

-0.52

opat

-0.51

 Loeb

-0.50

áli

-0.48

modb

-0.48

ształ

-0.48

 NSCoder

-0.47

 OnEnable

-0.47

Cox

-0.47

ücks

-0.46

POSITIVE LOGITS

 assignment

1.85

 Assignment

1.69

 Assignments

1.61

 assignments

1.61

Assignment

1.46

 ASSIGN

1.43

 ASSIGNMENT

1.39

assignment

1.36

Assignments

1.35

assignments

1.31

Activations Density 0.075%

references to homework assignments and related tasks

No Comments

No Known Activations