INDEX

Explanations

terms related to stopping or halting actions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Билгалдахарш

-0.98

Искәрмәләр

-0.76

 AssemblyVersion

-0.76

Personendaten

-0.74

LookAnd

-0.73

ResumeLayout

-0.72

LElement

-0.72

principalColumn

-0.70

ContentAlignment

-0.68

PointerException

-0.68

POSITIVE LOGITS

stop

1.63

Stop

1.41

STOP

1.27

 Stop

1.24

 STOP

1.04

 stop

1.01

stops

0.77

Stops

0.68

 Stops

0.62

Bye

0.58

Activations Density 0.084%

terms related to stopping or halting actions

No Comments

No Known Activations