INDEX

Explanations

specific function or command references within programming or coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

AndEndTag

-0.81

 itſelf

-0.79

 kasarigan

-0.76

ContentAsync

-0.75

SourceChecksum

-0.74

 raiſ

-0.74

principalColumn

-0.74

 transférez

-0.73

 ddelweddau

-0.72

AutoScaleMode

-0.71

POSITIVE LOGITS

don

0.43

que

0.42

 dont

0.41

 figure

0.38

Subjects

0.38

 pose

0.38

Vanguard

0.38

assuming

0.38

典型

0.38

 assuming

0.37

Activations Density 0.025%

specific function or command references within programming or coding contexts

No Comments

No Known Activations