INDEX

Explanations

terms related to timeframes and durations, particularly years and numbers associated with contracts or game statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

of

-0.58

to

-0.50

is

-0.49

 chiuso

-0.47

 Réponses

-0.46

 époux

-0.46

 with

-0.45

in

-0.45

 riconos

-0.45

 rius

-0.45

POSITIVE LOGITS

 faſt

1.09

 pleaſure

1.07

NUMX

1.03

 houſe

0.97

 ſmall

0.97

$_"

0.96

 purpoſe

0.94

Efq

0.93

^(@)

0.92

RunAsync

0.90

Activations Density 0.209%

terms related to timeframes and durations, particularly years and numbers associated with contracts or game statistics

No Comments

No Known Activations