INDEX

Explanations

terms related to orientation and alignment in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.55

-0.52

-0.51

<eos>

-0.49

As

-0.49

↵↵

-0.48

printStackTrace

-0.48

-0.47

POSITIVE LOGITS

 Houſe

0.91

 purpoſe

0.87

 Inscrivez

0.87

 Reſ

0.87

 Theſe

0.87

 credentials

0.86

 Anſ

0.85

ÍTULO

0.84

 ་་

0.84

 متعلقه

0.83

Activations Density 0.120%

terms related to orientation and alignment in various contexts

No Comments

No Known Activations