INDEX

Explanations

terms related to relative size or quantity comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

 متعلقه

-0.68

PerformLayout

-0.68

InstrumentedTest

-0.68

AnchorStyles

-0.65

providedIn

-0.65

StructEnd

-0.65

Filmographie

-0.64

SaveVideo

-0.60

 transfieras

-0.59

⟭

-0.57

POSITIVE LOGITS

 more

1.25

 worse

1.06

 better

1.03

 greater

0.98

 easier

0.98

 faster

0.96

 stronger

0.95

 harder

0.92

 sharper

0.91

 narrower

0.86

Activations Density 0.207%

terms related to relative size or quantity comparisons

No Comments

No Known Activations