INDEX

Explanations

references to specific individuals or names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

WriteTagHelper

-0.89

 CreateTagHelper

-0.89

twimg

-0.85

ValueStyle

-0.85

 Paglinawan

-0.71

ViewFeatures

-0.70

ContentAlignment

-0.69

 nahilalakip

-0.69

AndEndTag

-0.68

 unknownFields

-0.68

POSITIVE LOGITS

PerformLayout

0.42

Syl

0.42

PLW

0.41

 mnie

0.41

 apothe

0.41

ėjimo

0.41

ėjimas

0.41

KE

0.41

 sebastian

0.40

 commutation

0.40

Activations Density 0.467%

references to specific individuals or names

No Comments

No Known Activations