INDEX

Explanations

phrases indicating movement or direction, particularly those related to "up" and "out."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 للاسماء

-0.94

Diweddarwch

-0.93

WithIOException

-0.78

DebuggerNonUser

-0.77

Personensuche

-0.74

حياته

-0.73

 pleaſure

-0.73

utilisons

-0.70

LookAnd

-0.70

 GenerationType

-0.69

POSITIVE LOGITS

up

0.63

 round

0.62

 down

0.58

 away

0.53

far

0.52

 here

0.51

out

0.51

rip

0.50

 over

0.50

round

0.49

Activations Density 0.107%

phrases indicating movement or direction, particularly those related to "up" and "out."

No Comments

No Known Activations