INDEX

Explanations

phrases related to sequences in data or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Offisielt

-0.84

IsPostBack

-0.81

 kark

-0.78

::_('

-0.77

 للمعارف

-0.77

 validamos

-0.76

__*/

-0.76

 femininos

-0.75

 isolado

-0.75

 Arki

-0.74

POSITIVE LOGITS

 sequence

2.25

 sequences

2.11

 Sequence

2.09

Sequence

2.07

sequence

2.04

seq

1.98

 SEQUENCE

1.93

 Sequences

1.88

seq

1.77

Sequences

1.69

Activations Density 0.115%

phrases related to sequences in data or processes

No Comments

No Known Activations