INDEX

Explanations

terms related to increases or improvements 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 @ 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

-0.70

-0.66

</b>

-0.64

خصة

-0.64

<b>

-0.63

queiro

-0.61

 Vallarta

-0.59

 getattr

-0.59

 Kitts

-0.59

POSITIVE LOGITS

 RISE

1.32

rise

1.20

 rise

1.16

 rises

1.13

 ROSE

1.10

Asc

1.09

RISE

1.06

 rose

1.06

WriteBarrier

1.05

ROSE

1.03

Activations Density 0.196%

terms related to increases or improvements in various contexts

No Comments

No Known Activations