INDEX

Explanations

words related to various forms of 've' or 'living' in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

例句

-0.57

таратура

-0.57

viato

-0.56

migrationBuilder

-0.54

sourceType

-0.54

THUR

-0.52

Académie

-0.52

typeorm

-0.52

HOY

-0.51

tyd

-0.50

POSITIVE LOGITS

Ve

0.84

Ve

0.82

ve

0.76

 protoimpl

0.71

VE

0.71

ve

0.66

Tes

0.62

ChildScrollView

0.62

VE

0.61

 BoxFit

0.61

Activations Density 0.083%

words related to various forms of 've' or 'living' in different contexts

No Comments

No Known Activations