INDEX

Explanations

references to timeframes and procedural steps in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 tyres

-1.17

defence

-1.14

Defence

-1.13

 analysed

-1.08

 realised

-1.07

 Defence

-1.07

favourite

-1.06

 standardised

-1.06

 organised

-1.04

labour

-1.04

POSITIVE LOGITS

 Monfieur

1.05

 ་་

1.04

 pleaſure

1.04

 Anſ

0.97

 itſelf

0.92

 idéia

0.91

 Majefty

0.90

 geologic

0.89

 humor

0.88

 parlor

0.88

Activations Density 2.445%

references to timeframes and procedural steps in context

No Comments

No Known Activations