INDEX

Explanations

terms related to ranking or hierarchical positioning

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

</>

-0.81

MigrationBuilder

-0.72

verwijspagina

-0.69

 Jefus

-0.66

 purpoſe

-0.64

WriteTagHelper

-0.64

ContentAsync

-0.64

 utafitiHapana

-0.63

AccessorTable

-0.63

{{/

-0.63

POSITIVE LOGITS

 rank

2.21

 Rank

2.07

rank

2.06

Rank

1.93

 Rating

1.76

 rating

1.76

 RANK

1.70

 Ranks

1.65

 ranks

1.64

RANK

1.60

Activations Density 0.069%

terms related to ranking or hierarchical positioning

No Comments

No Known Activations