INDEX

Explanations

concepts related to understanding and interpreting meaning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 nakalista

-0.93

RenderAtEndOf

-0.87

NUMX

-0.75

expandindo

-0.71

 المعيارى

-0.70

ChildScrollView

-0.69

NewGuid

-0.64

PyTuple

-0.64

reactivex

-0.64

 يتيمه

-0.63

POSITIVE LOGITS

 meanings

1.31

 meaning

1.29

 Meaning

1.11

Meaning

1.10

meaning

1.07

 significado

0.93

 symbolism

0.93

 interpretations

0.89

 interpret

0.89

 MEAN

0.87

Activations Density 0.220%

concepts related to understanding and interpreting meaning

No Comments

No Known Activations