INDEX

Explanations

programming language keywords and data types

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

 '\\;'

-0.82

ThroughAttribute

-0.79

CodeAttribute

-0.76

 فريبيس

-0.76

Hochspringen

-0.73

OGND

-0.72

 تضيفلها

-0.70

WriteTagHelper

-0.69

Diwedd

-0.68

 Infórmanos

-0.68

POSITIVE LOGITS

 ActionResult

0.55

IActionResult

0.54

 rana

0.52

적

0.50

 CGSize

0.50

적으로

0.50

lý

0.49

ActionResult

0.48

FlowLayout

0.48

Activations Density 0.039%

programming language keywords and data types

No Comments

No Known Activations