INDEX

Explanations

actions and processes related to development and improvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

beforeEach

-0.51

Eloquent

-0.48

 aufge

-0.46

PointCloud

-0.45

لوم

-0.45

bukkit

-0.44

ImageField

-0.43

<eos>

-0.43

copyWith

-0.42

'+

-0.41

POSITIVE LOGITS

expandindo

0.95

 themſelves

0.76

 beginnetje

0.76

0.75

 itſelf

0.75

 myſelf

0.74

іга

0.74

 Theſe

0.73

ſelf

0.73

 Shakspeare

0.72

Activations Density 0.292%

actions and processes related to development and improvement

No Comments

No Known Activations