INDEX

Explanations

references to buttons in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

."</

-0.94

windowFixed

-0.85

OrWhiteSpace

-0.81

 Majefty

-0.80

 vorkommen

-0.76

 becauſe

-0.75

verständlich

-0.74

 hinweg

-0.74

Efq

-0.73

Referințe

-0.73

POSITIVE LOGITS

 buttons

2.34

 button

2.23

 Buttons

2.13

 Button

2.12

 BUTTON

2.04

button

1.99

buttons

1.94

Buttons

1.91

Button

1.85

BUTTON

1.80

Activations Density 0.058%

references to buttons in programming contexts

No Comments

No Known Activations