INDEX

Explanations

phrases emphasizing ownership or association

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ScopeManager

-0.93

\{\\

-0.81

 فريبيس

-0.72

 ReSharper

-0.71

 useNavigate

-0.69

InputBorder

-0.68

setDo

-0.68

 ArrayAdapter

-0.66

JdbcTemplate

-0.66

KeySpec

-0.64

POSITIVE LOGITS

 belong

0.82

 belongs

0.69

Fri

0.68

Graph

0.64

 bring

0.63

 belonged

0.60

 brought

0.60

Fri

0.60

friend

0.58

belong

0.56

Activations Density 0.126%

phrases emphasizing ownership or association

No Comments

No Known Activations