INDEX

Explanations

references to actions or conditions that imply consequences or outcomes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ThroughAttribute

-0.92

Datuak

-0.88

oredCriteria

-0.81

ModelAdmin

-0.80

tvguidetime

-0.80

EndInit

-0.79

itinéraire

-0.77

]--;

-0.77

 NDEBUG

-0.77

 >=",

-0.76

POSITIVE LOGITS

Must

0.38

кти

0.37

cu

0.37

Has

0.36

ществ

0.36

↵

0.36

nič

0.36

 transpired

0.35

Been

0.35

 Happens

0.34

Activations Density 0.667%

references to actions or conditions that imply consequences or outcomes

No Comments

No Known Activations