INDEX

Explanations

instances of the word "after" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 AttributeSet

-0.97

Efq

-0.96

ſelf

-0.88

 myſelf

-0.88

 Jefus

-0.85

 ་་

-0.84

complexContent

-0.82

Bronnen

-0.81

 TextAlign

-0.81

bibfield

-0.81

POSITIVE LOGITS

 after

4.28

after

3.86

 After

3.44

After

3.40

 AFTER

3.22

AFTER

3.15

 dopo

3.07

 setelah

2.84

 après

2.84

 após

2.80

Activations Density 0.127%

instances of the word "after" and its variations

No Comments

No Known Activations