INDEX

Explanations

references to cables and their uses in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GIVEREF

-1.04

Personensuche

-0.84

 Floren

-0.84

 CreateTagHelper

-0.80

CRF

-0.80

seamnă

-0.79

Попис

-0.79

 doInBackground

-0.78

 NIST

-0.78

 Hurts

-0.77

POSITIVE LOGITS

 cable

2.02

 Cable

1.94

 cables

1.81

 CABLE

1.78

Cable

1.74

cable

1.66

 Cables

1.50

cables

1.34

ケーブル

1.18

 Kabel

1.11

Activations Density 0.076%

references to cables and their uses in various contexts

No Comments

No Known Activations