INDEX

Explanations

punctuation marks in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ing

-1.17

обходи

-0.87

ly

-0.86

ting

-0.81

 orderId

-0.77

ING

-0.76

ming

-0.75

bing

-0.74

ActivityResult

-0.70

 Picchu

-0.70

POSITIVE LOGITS

0.99

、

0.85

„

0.79

0.77

 („

0.77

 resourceCulture

0.77

ERM

0.75

 Nürnberg

0.74

0.73

Activations Density 0.105%

punctuation marks in the text

No Comments

No Known Activations