INDEX

Explanations

references to unspecified or vague "something" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

kjø

-0.46

 käyt

-0.40

 tuturor

-0.40

 extinción

-0.40

VIAF

-0.40

 kveld

-0.40

 diariamente

-0.40

hånd

-0.39

 alcuna

-0.39

 جميع

-0.39

POSITIVE LOGITS

 something

2.08

something

1.87

Something

1.84

 Something

1.80

 SOMETHING

1.64

 somethin

1.55

ETHING

1.20

 someone

1.16

someone

1.13

 iets

1.10

Activations Density 0.090%

references to unspecified or vague "something" in various contexts

No Comments

No Known Activations