INDEX

Explanations

terms related to transformations 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 @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 ILogger

-1.00

 Houſe

-0.95

 Monfieur

-0.92

 Anſ

-0.89

 fubject

-0.88

 houſe

-0.88

 RSSSF

-0.87

 myſelf

-0.83

 auffi

-0.82

 bershka

-0.81

POSITIVE LOGITS

 transformation

1.00

 transformed

0.93

 transforming

0.88

Transformation

0.85

 Transformation

0.84

 transformations

0.82

 transform

0.80

transformation

0.74

transformed

0.72

 transforma

0.72

Activations Density 0.166%

terms related to transformations in various contexts

No Comments

No Known Activations