INDEX

Explanations

the word "it" 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 @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

CodeAttribute

-0.64

 فريبيس

-0.58

 متعلقه

-0.56

ideon

-0.56

siębior

-0.54

Efq

-0.53

swt

-0.53

VYMaps

-0.53

ControllerAdvice

-0.53

onViewCreated

-0.53

POSITIVE LOGITS

 turns

0.66

 remains

0.54

 seraient

0.53

 wouldn

0.53

 auraient

0.51

 appears

0.50

########.

0.50

 wasn

0.50

 beggars

0.50

ShouldBe

0.49

Activations Density 0.180%

the word "it" in various contexts

No Comments

No Known Activations