INDEX

Explanations

phrases that indicate progress or achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Cr

-0.53

 pulumi

-0.51

 GaAs

-0.50

<eos>

-0.48

erokee

-0.47

marvin

-0.46

 органы

-0.46

 antigas

-0.45

jandra

-0.45

]]

-0.44

POSITIVE LOGITS

为止

1.09

 preliminar

0.83

weile

0.83

 مرئيه

0.82

 epidemiological

0.80

 незавершена

0.79

 تضيفلها

0.77

 HasFactory

0.74

 bisherigen

0.74

ipedi

0.74

Activations Density 0.124%

phrases that indicate progress or achievements

No Comments

No Known Activations